CS-E Deep Learning Session 4: Convolutional Networks

Size: px
Start display at page:

Download "CS-E Deep Learning Session 4: Convolutional Networks"

Transcription

1 CS-E Deep Learning Session 4: Convolutional Networks Jyri Kivinen Aalto University 23 September 2015 Credits: Thanks to Tapani Raiko for slides material. CS-E Deep Learning Session 4: Convolutional Networks 23 September / 19

2 Some desiderata for pattern recognition systems (?) Stable and predictable response change to transforming (say shifted) input The ability to deal with varying-sized inputs (in terms of unit cardinality) and input patterns (in terms of their scale) Avoiding the need to learn properties that one can encode into the model easily Parsimonious representations. CS-E Deep Learning Session 4: Convolutional Networks 23 September / 19

3 Feed-forward networks for high-dimensional and highly variable content Imagine a set of 1000x1000 images (rather low-resolution images compared to what can be captured with even most mobile phone cameras these days) for training and to be analyzed by a regular feed-forward network, say an MLP. Suppose the model is to define a classifier, say classifying images to some predefined categories, like to interesting and to not interesting. One million (weight) connections per hidden unit in the first layer, even just for gray-scale images. Without e.g. parameter sharing, could well be a really hard problem to scale onto; e.g. too many parameters to fit well the data one has (curse of dimensionality). CS-E Deep Learning Session 4: Convolutional Networks 23 September / 19

4 Feed-forward networks to high-dimensional and highly variable content Imagine a set of 1000x1000 images (rather low-resolution images compared to what can be captured with even most mobile phone cameras these days) for training and to be analyzed by a regular feed-forward network, say an MLP. Suppose the model is to define a classifier, say classifying images to some predefined categories, like to interesting and to not interesting. How to deal with test images of (even slightly) different size? How would the unit activations be for an image and the image shifted? Good approaches for handling potential issues? CS-E Deep Learning Session 4: Convolutional Networks 23 September / 19

5 Convolutional (deterministic) feed-forward networks: On the main ingredients Grid-arrangement and position encoding: units in the input layer retain and hidden unit layer(s) are arranged to have stacked-grid-topology with co-ordinated position indexing. Local connectivity: each hidden unit receives input only from (its input layer) units with position within its so-called receptive field. Parameter sharing: Hidden unit layers consist of multiple grids of hidden units called feature planes, and parameters are shared within a feature plane; can be used to obtain translation equivariance (and then e.g. stability and predictability of response change due to shifted input). Pooling; used e.g. to obtain local translation invariance (e.g. to allow local spatial input deformations), reduce dimensions. CS-E Deep Learning Session 4: Convolutional Networks 23 September / 19

6 Convolutional networks: from full to local connections (example, credit: Tapani Raiko) CS-E Deep Learning Session 4: Convolutional Networks 23 September / 19

7 Convolutional networks: parameter sharing (example, credit: Tapani Raiko) CS-E Deep Learning Session 4: Convolutional Networks 23 September / 19

8 Convolutional networks: first layer without pooling (example, credit: Tapani Raiko) CS-E Deep Learning Session 4: Convolutional Networks 23 September / 19

9 Convolutional networks: first layer with pooling (example, credit: Tapani Raiko) CS-E Deep Learning Session 4: Convolutional Networks 23 September / 19

10 Convolutional networks: full network (example, credit: Tapani Raiko) CS-E Deep Learning Session 4: Convolutional Networks 23 September / 19

11 Convolutional vs. non-convolutional (Slide [credit]: Tapani Raiko) Number of weights (ignoring biases): = = Sizes of signals h: 28 28, , = 784, 7056, 3136 Compare to an example non-convolutional example: Weights: = = Signals: 784, 225, 144 Convolutional network has more signals but less params. Could we scale the networks to the 1000x1000 images? Would/should some of their properties change? CS-E Deep Learning Session 4: Convolutional Networks 23 September / 19

12 Some example application input types (Credit: Tapani Raiko) Tensor Single channel Multi-channel 1-D Raw audio (mono) Motion capture 2-D Audio + (S.T.) Fourier transform Game of Go 3-D Brain imaging Colour video CS-E Deep Learning Session 4: Convolutional Networks 23 September / 19

13 Some possible connectivity, parameter sharing, and pooling function variants Parameter sharing patterns per a convolutional layer: No sharing of biases Spatial parameter sharing patterns (e.g. tiled-convolutional) Input connectivity patterns of units within a feature plane: Overlapping (regular-convolutional) Non-overlapping (tiled-convolutional) Fixed pooling function variants: Linear functions: average-pooling Non-linear functions: max-pooling CS-E Deep Learning Session 4: Convolutional Networks 23 September / 19

14 But why called convolutional? As often in any F-F neural networks, the hidden units can be seen take as their input a linear combination of the activations by the units connecting to them (bias unit fixed to one, other units); they first linearly transform their input data, and then apply the activation function to get the unit activation/state. Implementing the linear transform computations per layer could be implemented in multiple ways. Computing convolutional-layer unit inputs can be computed via convolution/cross-correlation of the activations of the connecting-unit values by filter-kernels defined by the feature-plane specific weights (/filters). Highly parallellizable; don t even think about sliding windows! (Fast) Fourier-transform (FFT) - based approaches may be inconvenient/problematic (e.g. boundary handling issues). CS-E Deep Learning Session 4: Convolutional Networks 23 September / 19

15 Convolution-operator (Slide from Tapani Raiko) (w x)[t] = a w[a]x[t a] CS-E Deep Learning Session 4: Convolutional Networks 23 September / 19

16 Handling boundaries in convolutional layers Border units may need special treatment. Some boundary handling implementation variants, when doing the convolutions: Padd the inputs when computing the outputs: by zeroes or e.g. from input data: e.g. wrap-around borders Can be used to retain fixed grid size from input to output Don t padd inputs when computing the outputs: Each output unit receives the same number of connections from the input data; output grid dimensions are smaller. CS-E Deep Learning Session 4: Convolutional Networks 23 September / 19

17 Home exercises Familiarize with the Conv. Neural Networks (LeNet) tutorial: http: //deeplearning.net/tutorial/lenet.html. Reported task: Implement and experiment with gradient descent - based training of a convolutional (feed-forward) network; details on the next slide. CS-E Deep Learning Session 4: Convolutional Networks 23 September / 19

18 Home exercises Reported task: Implement and experiment with gradient descent - based training of a convolutional (feed-forward) network: Choose the details: data, network structure, etc., except: have at least one convolutional layer; have pooling. Experiment with the approach providing the following visualization: objective function evaluated on the training data as a function of the number of training epochs; could also plot further things such as learned network parameters, unit activations (as a response to some data), (other) important training diagnostics. Provide a description of your approach and the results in the report (providing the visualization(s) and most important lines of code). CS-E Deep Learning Session 4: Convolutional Networks 23 September / 19

19 Materials, references Gradients to inputs: Zeiler, Matthew D., and Rob Fergus. Visualizing and understanding convolutional networks. In Proc., European Conference on Computer Vision (ECCV), LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86 (1998) LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., & Jackel, L. D. Backpropagation applied to handwritten zip code recognition. Neural computation, 1(4), (1989) Waibel, A., Hanazawa, T., Hinton, G.E., Shikano, K., Lang, K.: Phoneme recognition using Time Delay Neural Networks. IEEE Trans. ASSP 37 (1989) CS-E Deep Learning Session 4: Convolutional Networks 23 September / 19

Understanding Convolutional Neural

Understanding Convolutional Neural Understanding Convolutional Neural Networks Understanding Convolutional Neural Networks David Stutz July 24th, 2014 David Stutz July 24th, 2014 0/53 1/53 Table of Contents - Table of Contents 1 Motivation

More information

A convolutional neural network to classify American Sign Language fingerspelling from depth and colour images

A convolutional neural network to classify American Sign Language fingerspelling from depth and colour images A convolutional neural network to classify American Sign Language fingerspelling from depth and colour images Ameen, SA and Vadera, S http://dx.doi.org/10.1111/exsy.12197 Title Authors Type URL A convolutional

More information

CSE Introduction to High-Perfomance Deep Learning ImageNet & VGG. Jihyung Kil

CSE Introduction to High-Perfomance Deep Learning ImageNet & VGG. Jihyung Kil CSE 5194.01 - Introduction to High-Perfomance Deep Learning ImageNet & VGG Jihyung Kil ImageNet Classification with Deep Convolutional Neural Networks Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton,

More information

COMP9444 Neural Networks and Deep Learning 5. Convolutional Networks

COMP9444 Neural Networks and Deep Learning 5. Convolutional Networks COMP9444 Neural Networks and Deep Learning 5. Convolutional Networks Textbook, Sections 6.2.2, 6.3, 7.9, 7.11-7.13, 9.1-9.5 COMP9444 17s2 Convolutional Networks 1 Outline Geometry of Hidden Unit Activations

More information

Efficient Deep Model Selection

Efficient Deep Model Selection Efficient Deep Model Selection Jose Alvarez Researcher Data61, CSIRO, Australia GTC, May 9 th 2017 www.josemalvarez.net conv1 conv2 conv3 conv4 conv5 conv6 conv7 conv8 softmax prediction???????? Num Classes

More information

Rich feature hierarchies for accurate object detection and semantic segmentation

Rich feature hierarchies for accurate object detection and semantic segmentation Rich feature hierarchies for accurate object detection and semantic segmentation Ross Girshick, Jeff Donahue, Trevor Darrell, Jitendra Malik UC Berkeley Tech Report @ http://arxiv.org/abs/1311.2524! Detection

More information

Flexible, High Performance Convolutional Neural Networks for Image Classification

Flexible, High Performance Convolutional Neural Networks for Image Classification Flexible, High Performance Convolutional Neural Networks for Image Classification Dan C. Cireşan, Ueli Meier, Jonathan Masci, Luca M. Gambardella, Jürgen Schmidhuber IDSIA, USI and SUPSI Manno-Lugano,

More information

A HMM-based Pre-training Approach for Sequential Data

A HMM-based Pre-training Approach for Sequential Data A HMM-based Pre-training Approach for Sequential Data Luca Pasa 1, Alberto Testolin 2, Alessandro Sperduti 1 1- Department of Mathematics 2- Department of Developmental Psychology and Socialisation University

More information

PMR5406 Redes Neurais e Lógica Fuzzy. Aula 5 Alguns Exemplos

PMR5406 Redes Neurais e Lógica Fuzzy. Aula 5 Alguns Exemplos PMR5406 Redes Neurais e Lógica Fuzzy Aula 5 Alguns Exemplos APPLICATIONS Two examples of real life applications of neural networks for pattern classification: RBF networks for face recognition FF networks

More information

An Artificial Neural Network Architecture Based on Context Transformations in Cortical Minicolumns

An Artificial Neural Network Architecture Based on Context Transformations in Cortical Minicolumns An Artificial Neural Network Architecture Based on Context Transformations in Cortical Minicolumns 1. Introduction Vasily Morzhakov, Alexey Redozubov morzhakovva@gmail.com, galdrd@gmail.com Abstract Cortical

More information

Convolutional Neural Networks (CNN)

Convolutional Neural Networks (CNN) Convolutional Neural Networks (CNN) Algorithm and Some Applications in Computer Vision Luo Hengliang Institute of Automation June 10, 2014 Luo Hengliang (Institute of Automation) Convolutional Neural Networks

More information

Motivation: Attention: Focusing on specific parts of the input. Inspired by neuroscience.

Motivation: Attention: Focusing on specific parts of the input. Inspired by neuroscience. Outline: Motivation. What s the attention mechanism? Soft attention vs. Hard attention. Attention in Machine translation. Attention in Image captioning. State-of-the-art. 1 Motivation: Attention: Focusing

More information

Object recognition and hierarchical computation

Object recognition and hierarchical computation Object recognition and hierarchical computation Challenges in object recognition. Fukushima s Neocognitron View-based representations of objects Poggio s HMAX Forward and Feedback in visual hierarchy Hierarchical

More information

Hierarchical Convolutional Features for Visual Tracking

Hierarchical Convolutional Features for Visual Tracking Hierarchical Convolutional Features for Visual Tracking Chao Ma Jia-Bin Huang Xiaokang Yang Ming-Husan Yang SJTU UIUC SJTU UC Merced ICCV 2015 Background Given the initial state (position and scale), estimate

More information

Do Deep Neural Networks Suffer from Crowding?

Do Deep Neural Networks Suffer from Crowding? Do Deep Neural Networks Suffer from Crowding? Anna Volokitin Gemma Roig ι Tomaso Poggio voanna@vision.ee.ethz.ch gemmar@mit.edu tp@csail.mit.edu Center for Brains, Minds and Machines, Massachusetts Institute

More information

Convolutional Neural Networks for Text Classification

Convolutional Neural Networks for Text Classification Convolutional Neural Networks for Text Classification Sebastian Sierra MindLab Research Group July 1, 2016 ebastian Sierra (MindLab Research Group) NLP Summer Class July 1, 2016 1 / 32 Outline 1 What is

More information

Convolutional Neural Networks for Estimating Left Ventricular Volume

Convolutional Neural Networks for Estimating Left Ventricular Volume Convolutional Neural Networks for Estimating Left Ventricular Volume Ryan Silva Stanford University rdsilva@stanford.edu Maksim Korolev Stanford University mkorolev@stanford.edu Abstract End-systolic and

More information

Using stigmergy to incorporate the time into artificial neural networks

Using stigmergy to incorporate the time into artificial neural networks Using stigmergy to incorporate the time into artificial neural networks Federico A. Galatolo, Mario G.C.A. Cimino, and Gigliola Vaglini Department of Information Engineering, University of Pisa, 56122

More information

Auto-Encoder Pre-Training of Segmented-Memory Recurrent Neural Networks

Auto-Encoder Pre-Training of Segmented-Memory Recurrent Neural Networks Auto-Encoder Pre-Training of Segmented-Memory Recurrent Neural Networks Stefan Glüge, Ronald Böck and Andreas Wendemuth Faculty of Electrical Engineering and Information Technology Cognitive Systems Group,

More information

Object Detectors Emerge in Deep Scene CNNs

Object Detectors Emerge in Deep Scene CNNs Object Detectors Emerge in Deep Scene CNNs Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, Antonio Torralba Presented By: Collin McCarthy Goal: Understand how objects are represented in CNNs Are

More information

Supplementary method. a a a. a a a. h h,w w, then the size of C will be ( h h + 1) ( w w + 1). The matrix K is

Supplementary method. a a a. a a a. h h,w w, then the size of C will be ( h h + 1) ( w w + 1). The matrix K is Deep earning Radiomics of Shear Wave lastography Significantly Improved Diagnostic Performance for Assessing iver Fibrosis in Chronic epatitis B: A Prospective Multicenter Study Supplementary method Mathematical

More information

Multi-attention Guided Activation Propagation in CNNs

Multi-attention Guided Activation Propagation in CNNs Multi-attention Guided Activation Propagation in CNNs Xiangteng He and Yuxin Peng (B) Institute of Computer Science and Technology, Peking University, Beijing, China pengyuxin@pku.edu.cn Abstract. CNNs

More information

MORE than 15 years after the early studies in Affective

MORE than 15 years after the early studies in Affective IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE, VOL. X, NO. X, MONTH 20XX 1 Learning Deep Physiological Models of Affect Héctor P. Martínez, Student Member, IEEE, Yoshua Bengio, and Georgios N. Yannakakis, Member,

More information

Networks and Hierarchical Processing: Object Recognition in Human and Computer Vision

Networks and Hierarchical Processing: Object Recognition in Human and Computer Vision Networks and Hierarchical Processing: Object Recognition in Human and Computer Vision Guest&Lecture:&Marius&Cătălin&Iordan&& CS&131&8&Computer&Vision:&Foundations&and&Applications& 01&December&2014 1.

More information

Task 1: Machine Learning with Spike-Timing-Dependent Plasticity (STDP)

Task 1: Machine Learning with Spike-Timing-Dependent Plasticity (STDP) DARPA Report Task1 for Year 1 (Q1-Q4) Task 1: Machine Learning with Spike-Timing-Dependent Plasticity (STDP) 1. Shortcomings of the deep learning approach to artificial intelligence It has been established

More information

Oscillatory Neural Network for Image Segmentation with Biased Competition for Attention

Oscillatory Neural Network for Image Segmentation with Biased Competition for Attention Oscillatory Neural Network for Image Segmentation with Biased Competition for Attention Tapani Raiko and Harri Valpola School of Science and Technology Aalto University (formerly Helsinki University of

More information

arxiv: v1 [cs.lg] 4 Feb 2019

arxiv: v1 [cs.lg] 4 Feb 2019 Machine Learning for Seizure Type Classification: Setting the benchmark Subhrajit Roy [000 0002 6072 5500], Umar Asif [0000 0001 5209 7084], Jianbin Tang [0000 0001 5440 0796], and Stefan Harrer [0000

More information

Audiovisual to Sign Language Translator

Audiovisual to Sign Language Translator Technical Disclosure Commons Defensive Publications Series July 17, 2018 Audiovisual to Sign Language Translator Manikandan Gopalakrishnan Follow this and additional works at: https://www.tdcommons.org/dpubs_series

More information

Visual interpretation in pathology

Visual interpretation in pathology 13 Visual interpretation in pathology Tissue architecture (alteration) evaluation e.g., for grading prostate cancer Immunohistochemistry (IHC) staining scoring e.g., HER2 in breast cancer (companion diagnostic

More information

A Deep Learning Approach for Subject Independent Emotion Recognition from Facial Expressions

A Deep Learning Approach for Subject Independent Emotion Recognition from Facial Expressions A Deep Learning Approach for Subject Independent Emotion Recognition from Facial Expressions VICTOR-EMIL NEAGOE *, ANDREI-PETRU BĂRAR *, NICU SEBE **, PAUL ROBITU * * Faculty of Electronics, Telecommunications

More information

High-Resolution Breast Cancer Screening with Multi-View Deep Convolutional Neural Networks

High-Resolution Breast Cancer Screening with Multi-View Deep Convolutional Neural Networks High-Resolution Breast Cancer Screening with Multi-View Deep Convolutional Neural Networks Krzysztof J. Geras Joint work with Kyunghyun Cho, Linda Moy, Gene Kim, Stacey Wolfson and Artie Shen. GTC 2017

More information

Y-Net: Joint Segmentation and Classification for Diagnosis of Breast Biopsy Images

Y-Net: Joint Segmentation and Classification for Diagnosis of Breast Biopsy Images Y-Net: Joint Segmentation and Classification for Diagnosis of Breast Biopsy Images Sachin Mehta 1, Ezgi Mercan 1, Jamen Bartlett 2, Donald Weaver 2, Joann G. Elmore 1, and Linda Shapiro 1 1 University

More information

Image Understanding and Machine Vision, Optical Society of America, June [8] H. Ney. The Use of a One-Stage Dynamic Programming Algorithm for

Image Understanding and Machine Vision, Optical Society of America, June [8] H. Ney. The Use of a One-Stage Dynamic Programming Algorithm for Image Understanding and Machine Vision, Optical Society of America, June 1989. [8] H. Ney. The Use of a One-Stage Dynamic Programming Algorithm for Connected Word Recognition. IEEE International Conference

More information

Less is More: Culling the Training Set to Improve Robustness of Deep Neural Networks

Less is More: Culling the Training Set to Improve Robustness of Deep Neural Networks Less is More: Culling the Training Set to Improve Robustness of Deep Neural Networks Yongshuai Liu, Jiyu Chen, and Hao Chen University of California, Davis {yshliu, jiych, chen}@ucdavis.edu Abstract. Deep

More information

Segmentation of Cell Membrane and Nucleus by Improving Pix2pix

Segmentation of Cell Membrane and Nucleus by Improving Pix2pix Segmentation of Membrane and Nucleus by Improving Pix2pix Masaya Sato 1, Kazuhiro Hotta 1, Ayako Imanishi 2, Michiyuki Matsuda 2 and Kenta Terai 2 1 Meijo University, Siogamaguchi, Nagoya, Aichi, Japan

More information

arxiv: v2 [cs.cv] 22 Mar 2018

arxiv: v2 [cs.cv] 22 Mar 2018 Deep saliency: What is learnt by a deep network about saliency? Sen He 1 Nicolas Pugeault 1 arxiv:1801.04261v2 [cs.cv] 22 Mar 2018 Abstract Deep convolutional neural networks have achieved impressive performance

More information

Data mining for Obstructive Sleep Apnea Detection. 18 October 2017 Konstantinos Nikolaidis

Data mining for Obstructive Sleep Apnea Detection. 18 October 2017 Konstantinos Nikolaidis Data mining for Obstructive Sleep Apnea Detection 18 October 2017 Konstantinos Nikolaidis Introduction: What is Obstructive Sleep Apnea? Obstructive Sleep Apnea (OSA) is a relatively common sleep disorder

More information

A Novel Capsule Neural Network Based Model For Drowsiness Detection Using Electroencephalography Signals

A Novel Capsule Neural Network Based Model For Drowsiness Detection Using Electroencephalography Signals A Novel Capsule Neural Network Based Model For Drowsiness Detection Using Electroencephalography Signals Luis Guarda Bräuning (1) Nicolas Astorga (1) Enrique López Droguett (1) Marcio Moura (2) Marcelo

More information

Biologically-Inspired Human Motion Detection

Biologically-Inspired Human Motion Detection Biologically-Inspired Human Motion Detection Vijay Laxmi, J. N. Carter and R. I. Damper Image, Speech and Intelligent Systems (ISIS) Research Group Department of Electronics and Computer Science University

More information

Reading Assignments: Lecture 18: Visual Pre-Processing. Chapters TMB Brain Theory and Artificial Intelligence

Reading Assignments: Lecture 18: Visual Pre-Processing. Chapters TMB Brain Theory and Artificial Intelligence Brain Theory and Artificial Intelligence Lecture 18: Visual Pre-Processing. Reading Assignments: Chapters TMB2 3.3. 1 Low-Level Processing Remember: Vision as a change in representation. At the low-level,

More information

Towards disentangling underlying explanatory factors Yoshua Bengio. July 13th, 2018 ICML 2018 Workshop on Learning with Limited Labels

Towards disentangling underlying explanatory factors Yoshua Bengio. July 13th, 2018 ICML 2018 Workshop on Learning with Limited Labels Towards disentangling underlying explanatory factors Yoshua Bengio July 13th, 2018 ICML 2018 Workshop on Learning with Limited Labels Generalizing Beyond i.i.d. Data Current ML theory is strongly dependent

More information

Early Diagnosis of Autism Disease by Multi-channel CNNs

Early Diagnosis of Autism Disease by Multi-channel CNNs Early Diagnosis of Autism Disease by Multi-channel CNNs Guannan Li 1,2, Mingxia Liu 2, Quansen Sun 1(&), Dinggang Shen 2(&), and Li Wang 2(&) 1 School of Computer Science and Engineering, Nanjing University

More information

Introduction to Machine Learning. Katherine Heller Deep Learning Summer School 2018

Introduction to Machine Learning. Katherine Heller Deep Learning Summer School 2018 Introduction to Machine Learning Katherine Heller Deep Learning Summer School 2018 Outline Kinds of machine learning Linear regression Regularization Bayesian methods Logistic Regression Why we do this

More information

QUANTIFICATION OF PROGRESSION OF RETINAL NERVE FIBER LAYER ATROPHY IN FUNDUS PHOTOGRAPH

QUANTIFICATION OF PROGRESSION OF RETINAL NERVE FIBER LAYER ATROPHY IN FUNDUS PHOTOGRAPH QUANTIFICATION OF PROGRESSION OF RETINAL NERVE FIBER LAYER ATROPHY IN FUNDUS PHOTOGRAPH Hyoun-Joong Kong *, Jong-Mo Seo **, Seung-Yeop Lee *, Hum Chung **, Dong Myung Kim **, Jeong Min Hwang **, Kwang

More information

Patients EEG Data Analysis via Spectrogram Image with a Convolution Neural Network

Patients EEG Data Analysis via Spectrogram Image with a Convolution Neural Network Patients EEG Data Analysis via Spectrogram Image with a Convolution Neural Network Longhao Yuan and Jianting Cao ( ) Graduate School of Engineering, Saitama Institute of Technology, Fusaiji 1690, Fukaya-shi,

More information

Recognizing Complex Mental States With Deep Hierarchical Features For Human-Robot Interaction

Recognizing Complex Mental States With Deep Hierarchical Features For Human-Robot Interaction In: Proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Hamburg, Germany (2015) Recognizing Mental States With Deep Hierarchical Features For Human-Robot Interaction

More information

A CONVOLUTION NEURAL NETWORK ALGORITHM FOR BRAIN TUMOR IMAGE SEGMENTATION

A CONVOLUTION NEURAL NETWORK ALGORITHM FOR BRAIN TUMOR IMAGE SEGMENTATION A CONVOLUTION NEURAL NETWORK ALGORITHM FOR BRAIN TUMOR IMAGE SEGMENTATION 1 Priya K, 2 Dr.O. Saraniya 1 PG Scholar, 2 Assistant Professor Department Of ECE Government College of Technology, Coimbatore,

More information

Question 1 Multiple Choice (8 marks)

Question 1 Multiple Choice (8 marks) Philadelphia University Student Name: Faculty of Engineering Student Number: Dept. of Computer Engineering First Exam, First Semester: 2015/2016 Course Title: Neural Networks and Fuzzy Logic Date: 19/11/2015

More information

Recognition of sign language gestures using neural networks

Recognition of sign language gestures using neural networks Recognition of sign language gestures using neural s Peter Vamplew Department of Computer Science, University of Tasmania GPO Box 252C, Hobart, Tasmania 7001, Australia vamplew@cs.utas.edu.au ABSTRACT

More information

Differences of Face and Object Recognition in Utilizing Early Visual Information

Differences of Face and Object Recognition in Utilizing Early Visual Information Differences of Face and Object Recognition in Utilizing Early Visual Information Peter Kalocsai and Irving Biederman Department of Psychology and Computer Science University of Southern California Los

More information

Skin cancer reorganization and classification with deep neural network

Skin cancer reorganization and classification with deep neural network Skin cancer reorganization and classification with deep neural network Hao Chang 1 1. Department of Genetics, Yale University School of Medicine 2. Email: changhao86@gmail.com Abstract As one kind of skin

More information

Automatic Classification of Perceived Gender from Facial Images

Automatic Classification of Perceived Gender from Facial Images Automatic Classification of Perceived Gender from Facial Images Joseph Lemley, Sami Abdul-Wahid, Dipayan Banik Advisor: Dr. Razvan Andonie SOURCE 2016 Outline 1 Introduction 2 Faces - Background 3 Faces

More information

Synthesis of Gadolinium-enhanced MRI for Multiple Sclerosis patients using Generative Adversarial Network

Synthesis of Gadolinium-enhanced MRI for Multiple Sclerosis patients using Generative Adversarial Network Medical Application of GAN Synthesis of Gadolinium-enhanced MRI for Multiple Sclerosis patients using Generative Adversarial Network Sumana Basu School of Computer Science McGill University 260727568 sumana.basu@mail.mcgill.ca

More information

CS4495 Computer Vision Introduction to Recognition. Aaron Bobick School of Interactive Computing

CS4495 Computer Vision Introduction to Recognition. Aaron Bobick School of Interactive Computing CS4495 Computer Vision Introduction to Recognition Aaron Bobick School of Interactive Computing What does recognition involve? Source: Fei Fei Li, Rob Fergus, Antonio Torralba. Verification: is that

More information

A Selective Attention Based Method for Visual Pattern Recognition

A Selective Attention Based Method for Visual Pattern Recognition A Selective Attention Based Method for Visual Pattern Recognition Albert Ali Salah (SALAH@Boun.Edu.Tr) Ethem Alpaydın (ALPAYDIN@Boun.Edu.Tr) Lale Akarun (AKARUN@Boun.Edu.Tr) Department of Computer Engineering;

More information

Using.a Saliency Map for Active Spatial Selective Attention: Implementation & Initial Results

Using.a Saliency Map for Active Spatial Selective Attention: Implementation & Initial Results Advances in Neural Information Processing Systems, Vol 6, San Mateo, CA 1994. Using.a Saliency Map for Active Spatial Selective Attention: Implementation & Initial Results Shumeet Baluja baluja@cs.cmu.edu

More information

Facial expression recognition with spatiotemporal local descriptors

Facial expression recognition with spatiotemporal local descriptors Facial expression recognition with spatiotemporal local descriptors Guoying Zhao, Matti Pietikäinen Machine Vision Group, Infotech Oulu and Department of Electrical and Information Engineering, P. O. Box

More information

Convolutional and LSTM Neural Networks

Convolutional and LSTM Neural Networks Convolutional and LSTM Neural Networks Vanessa Jurtz January 11, 2017 Contents Neural networks and GPUs Lasagne Peptide binding to MHC class II molecules Convolutional Neural Networks (CNN) Recurrent and

More information

Validating the Visual Saliency Model

Validating the Visual Saliency Model Validating the Visual Saliency Model Ali Alsam and Puneet Sharma Department of Informatics & e-learning (AITeL), Sør-Trøndelag University College (HiST), Trondheim, Norway er.puneetsharma@gmail.com Abstract.

More information

Reduction of Overfitting in Diabetes Prediction Using Deep Learning Neural Network

Reduction of Overfitting in Diabetes Prediction Using Deep Learning Neural Network Reduction of Overfitting in Diabetes Prediction Using Deep Learning Neural Network Akm Ashiquzzaman *, Abdul Kawsar Tushar *, Md. Rashedul Islam *, 1, and Jong-Myon Kim **, 2 * Department of CSE, University

More information

Summary and discussion of: Why Does Unsupervised Pre-training Help Deep Learning?

Summary and discussion of: Why Does Unsupervised Pre-training Help Deep Learning? Summary and discussion of: Why Does Unsupervised Pre-training Help Deep Learning? Statistics Journal Club, 36-825 Avinava Dubey and Mrinmaya Sachan and Jerzy Wieczorek December 3, 2014 1 Summary 1.1 Deep

More information

Computational Cognitive Neuroscience

Computational Cognitive Neuroscience Computational Cognitive Neuroscience Computational Cognitive Neuroscience Computational Cognitive Neuroscience *Computer vision, *Pattern recognition, *Classification, *Picking the relevant information

More information

Neuromorphic convolutional recurrent neural network for road safety or safety near the road

Neuromorphic convolutional recurrent neural network for road safety or safety near the road Neuromorphic convolutional recurrent neural network for road safety or safety near the road WOO-SUP HAN 1, IL SONG HAN 2 1 ODIGA, London, U.K. 2 Korea Advanced Institute of Science and Technology, Daejeon,

More information

Learning Classifier Systems (LCS/XCSF)

Learning Classifier Systems (LCS/XCSF) Context-Dependent Predictions and Cognitive Arm Control with XCSF Learning Classifier Systems (LCS/XCSF) Laurentius Florentin Gruber Seminar aus Künstlicher Intelligenz WS 2015/16 Professor Johannes Fürnkranz

More information

Attentional Masking for Pre-trained Deep Networks

Attentional Masking for Pre-trained Deep Networks Attentional Masking for Pre-trained Deep Networks IROS 2017 Marcus Wallenberg and Per-Erik Forssén Computer Vision Laboratory Department of Electrical Engineering Linköping University 2014 2017 Per-Erik

More information

Incorporation of Imaging-Based Functional Assessment Procedures into the DICOM Standard Draft version 0.1 7/27/2011

Incorporation of Imaging-Based Functional Assessment Procedures into the DICOM Standard Draft version 0.1 7/27/2011 Incorporation of Imaging-Based Functional Assessment Procedures into the DICOM Standard Draft version 0.1 7/27/2011 I. Purpose Drawing from the profile development of the QIBA-fMRI Technical Committee,

More information

Why did the network make this prediction?

Why did the network make this prediction? Why did the network make this prediction? Ankur Taly (Google Inc.) Joint work with Mukund Sundararajan and Qiqi Yan Some Deep Learning Successes Source: https://www.cbsinsights.com Deep Neural Networks

More information

DeepASL: Enabling Ubiquitous and Non-Intrusive Word and Sentence-Level Sign Language Translation

DeepASL: Enabling Ubiquitous and Non-Intrusive Word and Sentence-Level Sign Language Translation DeepASL: Enabling Ubiquitous and Non-Intrusive Word and Sentence-Level Sign Language Translation Biyi Fang Michigan State University ACM SenSys 17 Nov 6 th, 2017 Biyi Fang (MSU) Jillian Co (MSU) Mi Zhang

More information

Shu Kong. Department of Computer Science, UC Irvine

Shu Kong. Department of Computer Science, UC Irvine Ubiquitous Fine-Grained Computer Vision Shu Kong Department of Computer Science, UC Irvine Outline 1. Problem definition 2. Instantiation 3. Challenge 4. Fine-grained classification with holistic representation

More information

Convolutional and LSTM Neural Networks

Convolutional and LSTM Neural Networks Convolutional and LSTM Neural Networks Vanessa Jurtz January 12, 2016 Contents Neural networks and GPUs Lasagne Peptide binding to MHC class II molecules Convolutional Neural Networks (CNN) Recurrent and

More information

Principals of Object Perception

Principals of Object Perception Principals of Object Perception Elizabeth S. Spelke COGNITIVE SCIENCE 14, 29-56 (1990) Cornell University Summary Infants perceive object by analyzing tree-dimensional surface arrangements and motions.

More information

Visual semantics: image elements. Symbols Objects People Poses

Visual semantics: image elements. Symbols Objects People Poses Visible Partisanship Polmeth XXXIII, Rice University, July 22, 2016 Convolutional Neural Networks for the Analysis of Political Images L. Jason Anastasopoulos ljanastas@uga.edu (University of Georgia,

More information

A Perceptron Reveals the Face of Sex

A Perceptron Reveals the Face of Sex A Perceptron Reveals the Face of Sex Michael S. Gray, David T. Lawrence, Beatrice A. Golomb, and Terrence J. Sejnowski April 23,1993 Technical Report INC-9303 Institute for Neural Computation University

More information

Satoru Hiwa, 1 Kenya Hanawa, 2 Ryota Tamura, 2 Keisuke Hachisuka, 3 and Tomoyuki Hiroyasu Introduction

Satoru Hiwa, 1 Kenya Hanawa, 2 Ryota Tamura, 2 Keisuke Hachisuka, 3 and Tomoyuki Hiroyasu Introduction Computational Intelligence and Neuroscience Volume 216, Article ID 1841945, 9 pages http://dx.doi.org/1.1155/216/1841945 Research Article Analyzing Brain Functions by Subject Classification of Functional

More information

Analysis of in-vivo extracellular recordings. Ryan Morrill Bootcamp 9/10/2014

Analysis of in-vivo extracellular recordings. Ryan Morrill Bootcamp 9/10/2014 Analysis of in-vivo extracellular recordings Ryan Morrill Bootcamp 9/10/2014 Goals for the lecture Be able to: Conceptually understand some of the analysis and jargon encountered in a typical (sensory)

More information

An Auditory System Modeling in Sound Source Localization

An Auditory System Modeling in Sound Source Localization An Auditory System Modeling in Sound Source Localization Yul Young Park The University of Texas at Austin EE381K Multidimensional Signal Processing May 18, 2005 Abstract Sound localization of the auditory

More information

ACUTE LEUKEMIA CLASSIFICATION USING CONVOLUTION NEURAL NETWORK IN CLINICAL DECISION SUPPORT SYSTEM

ACUTE LEUKEMIA CLASSIFICATION USING CONVOLUTION NEURAL NETWORK IN CLINICAL DECISION SUPPORT SYSTEM ACUTE LEUKEMIA CLASSIFICATION USING CONVOLUTION NEURAL NETWORK IN CLINICAL DECISION SUPPORT SYSTEM Thanh.TTP 1, Giao N. Pham 1, Jin-Hyeok Park 1, Kwang-Seok Moon 2, Suk-Hwan Lee 3, and Ki-Ryong Kwon 1

More information

Highly Accurate Brain Stroke Diagnostic System and Generative Lesion Model. Junghwan Cho, Ph.D. CAIDE Systems, Inc. Deep Learning R&D Team

Highly Accurate Brain Stroke Diagnostic System and Generative Lesion Model. Junghwan Cho, Ph.D. CAIDE Systems, Inc. Deep Learning R&D Team Highly Accurate Brain Stroke Diagnostic System and Generative Lesion Model Junghwan Cho, Ph.D. CAIDE Systems, Inc. Deep Learning R&D Team Established in September, 2016 at 110 Canal st. Lowell, MA 01852,

More information

Modeling the Deployment of Spatial Attention

Modeling the Deployment of Spatial Attention 17 Chapter 3 Modeling the Deployment of Spatial Attention 3.1 Introduction When looking at a complex scene, our visual system is confronted with a large amount of visual information that needs to be broken

More information

The Impact of Visual Saliency Prediction in Image Classification

The Impact of Visual Saliency Prediction in Image Classification Dublin City University Insight Centre for Data Analytics Universitat Politecnica de Catalunya Escola Tècnica Superior d Enginyeria de Telecomunicacions de Barcelona Eric Arazo Sánchez The Impact of Visual

More information

Perception & Attention. Perception is the best understood cognitive function, esp in terms of underlying biological substrates.

Perception & Attention. Perception is the best understood cognitive function, esp in terms of underlying biological substrates. Perception & Attention Perception is the best understood cognitive function, esp in terms of underlying biological substrates. Perception & Attention Perception is the best understood cognitive function,

More information

CS6501: Deep Learning for Visual Recognition. GenerativeAdversarial Networks (GANs)

CS6501: Deep Learning for Visual Recognition. GenerativeAdversarial Networks (GANs) CS6501: Deep Learning for Visual Recognition GenerativeAdversarial Networks (GANs) Today s Class Adversarial Examples Input Optimization Generative Adversarial Networks (GANs) Conditional GANs Style-Transfer

More information

B657: Final Project Report Holistically-Nested Edge Detection

B657: Final Project Report Holistically-Nested Edge Detection B657: Final roject Report Holistically-Nested Edge Detection Mingze Xu & Hanfei Mei May 4, 2016 Abstract Holistically-Nested Edge Detection (HED), which is a novel edge detection method based on fully

More information

Shu Kong. Department of Computer Science, UC Irvine

Shu Kong. Department of Computer Science, UC Irvine Ubiquitous Fine-Grained Computer Vision Shu Kong Department of Computer Science, UC Irvine Outline 1. Problem definition 2. Instantiation 3. Challenge and philosophy 4. Fine-grained classification with

More information

ITERATIVELY TRAINING CLASSIFIERS FOR CIRCULATING TUMOR CELL DETECTION

ITERATIVELY TRAINING CLASSIFIERS FOR CIRCULATING TUMOR CELL DETECTION ITERATIVELY TRAINING CLASSIFIERS FOR CIRCULATING TUMOR CELL DETECTION Yunxiang Mao 1, Zhaozheng Yin 1, Joseph M. Schober 2 1 Missouri University of Science and Technology 2 Southern Illinois University

More information

Lateral Geniculate Nucleus (LGN)

Lateral Geniculate Nucleus (LGN) Lateral Geniculate Nucleus (LGN) What happens beyond the retina? What happens in Lateral Geniculate Nucleus (LGN)- 90% flow Visual cortex Information Flow Superior colliculus 10% flow Slide 2 Information

More information

Deep Learning for Lip Reading using Audio-Visual Information for Urdu Language

Deep Learning for Lip Reading using Audio-Visual Information for Urdu Language Deep Learning for Lip Reading using Audio-Visual Information for Urdu Language Muhammad Faisal Information Technology University Lahore m.faisal@itu.edu.pk Abstract Human lip-reading is a challenging task.

More information

Formulating Emotion Perception as a Probabilistic Model with Application to Categorical Emotion Classification

Formulating Emotion Perception as a Probabilistic Model with Application to Categorical Emotion Classification Formulating Emotion Perception as a Probabilistic Model with Application to Categorical Emotion Classification Reza Lotfian and Carlos Busso Multimodal Signal Processing (MSP) lab The University of Texas

More information

Frequency Tracking: LMS and RLS Applied to Speech Formant Estimation

Frequency Tracking: LMS and RLS Applied to Speech Formant Estimation Aldebaro Klautau - http://speech.ucsd.edu/aldebaro - 2/3/. Page. Frequency Tracking: LMS and RLS Applied to Speech Formant Estimation ) Introduction Several speech processing algorithms assume the signal

More information

THE data used in this project is provided. SEIZURE forecasting systems hold promise. Seizure Prediction from Intracranial EEG Recordings

THE data used in this project is provided. SEIZURE forecasting systems hold promise. Seizure Prediction from Intracranial EEG Recordings 1 Seizure Prediction from Intracranial EEG Recordings Alex Fu, Spencer Gibbs, and Yuqi Liu 1 INTRODUCTION SEIZURE forecasting systems hold promise for improving the quality of life for patients with epilepsy.

More information

Representational similarity analysis

Representational similarity analysis School of Psychology Representational similarity analysis Dr Ian Charest Representational similarity analysis representational dissimilarity matrices (RDMs) stimulus (e.g. images, sounds, other experimental

More information

Chapter 1. Introduction

Chapter 1. Introduction Chapter 1 Introduction Artificial neural networks are mathematical inventions inspired by observations made in the study of biological systems, though loosely based on the actual biology. An artificial

More information

Using Deep Convolutional Networks for Gesture Recognition in American Sign Language

Using Deep Convolutional Networks for Gesture Recognition in American Sign Language Using Deep Convolutional Networks for Gesture Recognition in American Sign Language Abstract In the realm of multimodal communication, sign language is, and continues to be, one of the most understudied

More information

! Can hear whistle? ! Where are we on course map? ! What we did in lab last week. ! Psychoacoustics

! Can hear whistle? ! Where are we on course map? ! What we did in lab last week. ! Psychoacoustics 2/14/18 Can hear whistle? Lecture 5 Psychoacoustics Based on slides 2009--2018 DeHon, Koditschek Additional Material 2014 Farmer 1 2 There are sounds we cannot hear Depends on frequency Where are we on

More information

Hierarchical Conflict Propagation: Sequence Learning in a Recurrent Deep Neural Network

Hierarchical Conflict Propagation: Sequence Learning in a Recurrent Deep Neural Network Hierarchical Conflict Propagation: Sequence Learning in a Recurrent Deep Neural Network Andrew J.R. Simpson #1 # Centre for Vision, Speech and Signal Processing, University of Surrey Surrey, UK 1 Andrew.Simpson@Surrey.ac.uk

More information

Speech recognition in noisy environments: A survey

Speech recognition in noisy environments: A survey T-61.182 Robustness in Language and Speech Processing Speech recognition in noisy environments: A survey Yifan Gong presented by Tapani Raiko Feb 20, 2003 About the Paper Article published in Speech Communication

More information

Sign Language Recognition using Convolutional Neural Networks

Sign Language Recognition using Convolutional Neural Networks Sign Language Recognition using Convolutional Neural Networks Lionel Pigou, Sander Dieleman, Pieter-Jan Kindermans, Benjamin Schrauwen Ghent University, ELIS, Belgium Abstract. There is an undeniable communication

More information

A Brain Computer Interface System For Auto Piloting Wheelchair

A Brain Computer Interface System For Auto Piloting Wheelchair A Brain Computer Interface System For Auto Piloting Wheelchair Reshmi G, N. Kumaravel & M. Sasikala Centre for Medical Electronics, Dept. of Electronics and Communication Engineering, College of Engineering,

More information

Multilayer Perceptron Neural Network Classification of Malignant Breast. Mass

Multilayer Perceptron Neural Network Classification of Malignant Breast. Mass Multilayer Perceptron Neural Network Classification of Malignant Breast Mass Joshua Henry 12/15/2017 henry7@wisc.edu Introduction Breast cancer is a very widespread problem; as such, it is likely that

More information