Networks and Hierarchical Processing: Object Recognition in Human and Computer Vision
|
|
|
- Bernice Walker
- 6 years ago
- Views:
Transcription
1 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
2
3 1. Processing Pathways in the Human Visual System what and where pathways building features in the ventral stream 2. Hierarchical Pattern Recognition Systems early stages: small scale neural network injecting neuroscience knowledge into design 3. Third Age of the Neural Network: Modern Deep Nets extremely large scale ( data + computation ) sudden, huge performance boost for recognition Roadmap 23
4 From Retina to Cortex world retina (compression) LGN V1 visual cortex (expansion) Processing Pathways review 7
5 The Flow of Information IT IT Weiner & Grill-Spector (2012) Processing Pathways review 35
6 V1 Retina Van Essen (1991) Processing Pathways review 36
7 Specialization: What and Where Pathways monkey lesion studies Mishkin & Ungerleider 1982 Processing Pathways what and where pathways 37
8 Specialization: What and Where Pathways monkey lesion studies lesion where pathway: difficulty in spatial reasoning lesion what pathway: difficulty in object recognition Mishkin & Ungerleider 1982 Processing Pathways what and where pathways 37
9 Specialization: What and Where Pathways monkey lesion studies lesion where pathway: difficulty in spatial reasoning lesion what pathway: difficulty in object recognition Mishkin & Ungerleider 1982 Processing Pathways what and where pathways 37
10 Object Recognition: The What Pathway DiCarlo & Cox (2007) Processing Pathways building features in the ventral stream 38
11 Object Recognition: The What Pathway V1 IT Freeman & Simoncelli (2011), Tanaka (1997) Processing Pathways building features in the ventral stream 39
12 Object Recognition: Building Features and Invariance visual processing is done in stages each area performs a transformation on its inputs invariance is built gradually across many successive steps DiCarlo & Cox (2007) Processing Pathways key points 10 3
13 2. Hierarchical Pattern Recognition Systems neuroscience-inspired computer vision Hierarchical Computation 11 3
14 Neocognitron: Neural Network Layer 2 Layer 1 Cell Layer 3 Hierarchical Computation neocognitron 12 3
15 Neocognitron: Neural Network Fukushima (1988) Hierarchical Computation neocognitron 13 3
16 Neocognitron: Neural Network input layer S-cell layer C-cell layer Fukushima (1988) Hierarchical Computation neocognitron 13 3
17 Neocognitron: S-Cell C-cell layer / input layer S-cell layer C-cell layer LEARNING SUM THRESHOLD Fukushima (1988) Hierarchical Computation neocognitron 14 3
18 Neocognitron: S-Cell figure courtesy of A. Alahi Hierarchical Computation neocognitron 15 3
19 Neocognitron: C-Cell Pooling building position invariance Fukushima (1988) Hierarchical Computation neocognitron 16 3
20 Neocognitron: Network input S-cell C-cell S-cell C-cell S-cell C-cell S-cell C-cell Fukushima (1988) Hierarchical Computation neocognitron 17 3
21 Neocognitron: Network input S-cell C-cell S-cell C-cell S-cell C-cell S-cell C-cell Fukushima (1988) Hierarchical Computation neocognitron 17 3
22 Neocognitron: Network input S-cell C-cell S-cell C-cell S-cell C-cell S-cell C-cell Fukushima (1988) Hierarchical Computation neocognitron 17 3
23 Neocognitron: Network input S-cell C-cell S-cell C-cell S-cell C-cell S-cell C-cell Fukushima (1988) Hierarchical Computation neocognitron 17 3
24 Neocognitron: Robust Results Fukushima (1988) Hierarchical Computation neocognitron 18 3
25 Neocognitron biologically inspired hierarchical processing pipeline invariance is built gradually across many successive steps simple neural network solves complicated non-linear problem input layer S-cell layer C-cell layer Fukushima (1988) Hierarchical Computation neocognitron key points 19 3
26 Feed-Forward Object Recognition Model Hubel & Wiesel (1962), Riesenhuber & Poggio (1999), Serre et al. (2007) Hierarchical Computation feed-forward model 20 3
27 Feed-Forward Object Recognition Model Hubel & Wiesel (1962), Riesenhuber & Poggio (1999), Serre et al. (2007) Hierarchical Computation feed-forward model 20 3
28 Feed-Forward Object Recognition Model task: is there an animal in the picture? Serre et al. (2007) Hierarchical Computation feed-forward model 21 3
29 Feed-Forward Object Recognition Model task: is there an animal in the picture? Serre et al. (2007) Hierarchical Computation feed-forward model 22 3
30 Feed-Forward Object Recognition Model task: is there an animal in the picture? Serre et al. (2007) Hierarchical Computation feed-forward model 22 3
31
32 Feed-Forward Object Recognition Model task: is there an animal in the picture? Serre et al. (2007) Hierarchical Computation feed-forward model 24 3
33 Feed-Forward Object Recognition Model biologically-inspired processing pipeline patches receptive fields building invariance hierarchical processing major drawback? no feedback Serre et al. (2007) Hierarchical Computation feed-forward model key points 25 3
34 Discussion
35 Discussion how closely should we aim to copy human vision? is reverse-engineering human vision a self-imposed limitation? perfect recognition vs. visual understanding?
36 3. Modern Neural Networks extremely large scale data and computation Modern Neural Networks 27 3
37 Deep Convolutional Neural Network 650,000 cells 60,000,000 parameters input convolution pooling convolution pooling fully-connected Krizhevsky et al. (2013) Modern Neural Networks deep CNN 28 3
38 Deep Convolutional Neural Network 650,000 cells 60,000,000 parameters input convolution pooling convolution pooling fully-connected Krizhevsky et al. (2013) Modern Neural Networks deep CNN 28 3
39 Deep Convolutional Neural Network Want to know more about state-of-the-art neural networks? CS 231N Winter QT 2015 Fei-Fei Li & Andrej Karpathy Modern Neural Networks CS 231N 29 3
40 Object Recognition: Building Features and Invariance visual processing is done in stages each area performs a transformation on its inputs invariance is built gradually across many successive steps DiCarlo & Cox (2007) Processing Pathways key points 30 3
41 Feed-Forward Object Recognition Model biologically-inspired processing pipeline patches receptive fields building invariance hierarchical processing major drawbacks? no feedback much less complex than human vision Serre et al. (2007) Hierarchical Computation feed-forward model key points 31 3
42 Deep Convolutional Neural Network extremely large scale data and computation sudden, huge performance boost for recognition if you want to know more, take CS 231N in Winter QT Krizhevsky et al. (2013) Modern Neural Networks deep CNN key points 32 3
43 End-Quarter Feedback Forms
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
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
using deep learning models to understand visual cortex
using deep learning models to understand visual cortex 11-785 Introduction to Deep Learning Fall 2017 Michael Tarr Department of Psychology Center for the Neural Basis of Cognition this lecture A bit out
Just One View: Invariances in Inferotemporal Cell Tuning
Just One View: Invariances in Inferotemporal Cell Tuning Maximilian Riesenhuber Tomaso Poggio Center for Biological and Computational Learning and Department of Brain and Cognitive Sciences Massachusetts
Cognitive Modelling Themes in Neural Computation. Tom Hartley
Cognitive Modelling Themes in Neural Computation Tom Hartley t.hartley@psychology.york.ac.uk Typical Model Neuron x i w ij x j =f(σw ij x j ) w jk x k McCulloch & Pitts (1943), Rosenblatt (1957) Net input:
Adventures into terra incognita
BEWARE: These are preliminary notes. In the future, they will become part of a textbook on Visual Object Recognition. Chapter VI. Adventures into terra incognita In primary visual cortex there are neurons
Deep Neural Networks Rival the Representation of Primate IT Cortex for Core Visual Object Recognition
Deep Neural Networks Rival the Representation of Primate IT Cortex for Core Visual Object Recognition Charles F. Cadieu, Ha Hong, Daniel L. K. Yamins, Nicolas Pinto, Diego Ardila, Ethan A. Solomon, Najib
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
Shape Representation in V4: Investigating Position-Specific Tuning for Boundary Conformation with the Standard Model of Object Recognition
massachusetts institute of technology computer science and artificial intelligence laboratory Shape Representation in V4: Investigating Position-Specific Tuning for Boundary Conformation with the Standard
A quantitative theory of immediate visual recognition
A quantitative theory of immediate visual recognition Thomas Serre, Gabriel Kreiman, Minjoon Kouh, Charles Cadieu, Ulf Knoblich and Tomaso Poggio Center for Biological and Computational Learning McGovern
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
Invariant Recognition Shapes Neural Representations of Visual Input
Annu. Rev. Vis. Sci. 2018. 4:403 22 First published as a Review in Advance on July 27, 2018 The Annual Review of Vision Science is online at vision.annualreviews.org https://doi.org/10.1146/annurev-vision-091517-034103
Visual Categorization: How the Monkey Brain Does It
Visual Categorization: How the Monkey Brain Does It Ulf Knoblich 1, Maximilian Riesenhuber 1, David J. Freedman 2, Earl K. Miller 2, and Tomaso Poggio 1 1 Center for Biological and Computational Learning,
Eccentricity Dependent Deep Neural Networks: Modeling Invariance in Human Vision
Eccentricity Dependent Deep Neural Networks: Modeling Invariance in Human Vision Francis X. Chen, Gemma Roig, Leyla Isik, Xavier Boix and Tomaso Poggio Center for Brains, Minds and Machines, Massachusetts
IN this paper we examine the role of shape prototypes in
On the Role of Shape Prototypes in Hierarchical Models of Vision Michael D. Thomure, Melanie Mitchell, and Garrett T. Kenyon To appear in Proceedings of the International Joint Conference on Neural Networks
Perception & Attention
Perception & Attention Perception is effortless but its underlying mechanisms are incredibly sophisticated. Biology of the visual system Representations in primary visual cortex and Hebbian learning Object
PHY3111 Mid-Semester Test Study. Lecture 2: The hierarchical organisation of vision
PHY3111 Mid-Semester Test Study Lecture 2: The hierarchical organisation of vision 1. Explain what a hierarchically organised neural system is, in terms of physiological response properties of its neurones.
Reading Assignments: Lecture 5: Introduction to Vision. None. Brain Theory and Artificial Intelligence
Brain Theory and Artificial Intelligence Lecture 5:. Reading Assignments: None 1 Projection 2 Projection 3 Convention: Visual Angle Rather than reporting two numbers (size of object and distance to observer),
Probabilistic Models of the Cortex: Stat 271. Alan L. Yuille. UCLA.
Probabilistic Models of the Cortex: Stat 271. Alan L. Yuille. UCLA. Goals of the Course To give an introduction to the state of the art computational models of the mammalian visual cortex. To describe
Primary Visual Pathways (I)
Primary Visual Pathways (I) Introduction to Computational and Biological Vision CS 202-1-5261 Computer Science Department, BGU Ohad Ben-Shahar Where does visual information go from the eye? Where does
CS294-6 (Fall 2004) Recognizing People, Objects and Actions Lecture: January 27, 2004 Human Visual System
CS294-6 (Fall 2004) Recognizing People, Objects and Actions Lecture: January 27, 2004 Human Visual System Lecturer: Jitendra Malik Scribe: Ryan White (Slide: layout of the brain) Facts about the brain:
Neural representation of action sequences: how far can a simple snippet-matching model take us?
Neural representation of action sequences: how far can a simple snippet-matching model take us? Cheston Tan Institute for Infocomm Research Singapore cheston@mit.edu Jedediah M. Singer Boston Children
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
The Visual System. Cortical Architecture Casagrande February 23, 2004
The Visual System Cortical Architecture Casagrande February 23, 2004 Phone: 343-4538 Email: vivien.casagrande@mcmail.vanderbilt.edu Office: T2302 MCN Required Reading Adler s Physiology of the Eye Chapters
A Theory of Object Recognition: Computations and Circuits in the Feedforward Path of the Ventral Stream in Primate Visual Cortex
massachusetts institute of technology computer science and artificial intelligence laboratory A Theory of Object Recognition: Computations and Circuits in the Feedforward Path of the Ventral Stream in
Object vision (Chapter 4)
Object vision (Chapter 4) Lecture 8 Jonathan Pillow Sensation & Perception (PSY 345 / NEU 325) Princeton University, Spring 2015 1 Outline for today: Chap 3: adaptation Chap 4: intro to object vision gestalt
A Theory of Object Recognition: Computations and Circuits in the Feedforward Path of the Ventral Stream in Primate Visual Cortex
massachusetts institute of technology computer science and artificial intelligence laboratory A Theory of Object Recognition: Computations and Circuits in the Feedforward Path of the Ventral Stream in
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
Neural Mechanisms Underlying Visual Object Recognition
Neural Mechanisms Underlying Visual Object Recognition ARASH AFRAZ, DANIEL L.K. YAMINS, AND JAMES J. DICARLO Department of Brain and Cognitive Sciences and McGovern Institute for Brain Research, Massachusetts
A Detailed Look at Scale and Translation Invariance in a Hierarchical Neural Model of Visual Object Recognition
@ MIT massachusetts institute of technology artificial intelligence laboratory A Detailed Look at Scale and Translation Invariance in a Hierarchical Neural Model of Visual Object Recognition Robert Schneider
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,
Photoreceptors Rods. Cones
Photoreceptors Rods Cones 120 000 000 Dim light Prefer wavelength of 505 nm Monochromatic Mainly in periphery of the eye 6 000 000 More light Different spectral sensitivities!long-wave receptors (558 nm)
Attentive Stereoscopic Object Recognition
Attentive Stereoscopic Object Recognition Frederik Beuth, Jan Wiltschut, and Fred H. Hamker Chemnitz University of Technology, Strasse der Nationen 62, 09107 Chemnitz, Germany frederik.beuth@cs.tu-chemnitz.de,wiltschj@uni-muenster.de,
Information and neural computations
Information and neural computations Why quantify information? We may want to know which feature of a spike train is most informative about a particular stimulus feature. We may want to know which feature
Object recognition in cortex: Neural mechanisms, and possible roles for attention
Object recognition in cortex: Neural mechanisms, and possible roles for attention Maximilian Riesenhuber Department of Neuroscience Georgetown University Medical Center Washington, DC 20007 phone: 202-687-9198
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,
Chapter 3: 2 visual systems
Chapter 3: 2 visual systems Overview Explain the significance of the turn to the brain in cognitive science Explain Mishkin and Ungerleider s hypothesis that there are two distinct visual systems Outline
A quantitative theory of immediate visual recognition
B2v8:06a=w ðdec 200Þ:c XML:ver::0: PBR V6 : 6004 Prod:Type: pp:8ðcol:fig::nilþ ED: PAGN: SCAN: Cisek, Drew & Kalaska (Eds.) Progress in Brain Research, Vol. 6 ISSN 00-62 Copyright r 200 Elsevier B.V. All
Continuous transformation learning of translation invariant representations
Exp Brain Res (21) 24:255 27 DOI 1.17/s221-1-239- RESEARCH ARTICLE Continuous transformation learning of translation invariant representations G. Perry E. T. Rolls S. M. Stringer Received: 4 February 29
A Hubel Wiesel Model of Early Concept Generalization Based on Local Correlation of Input Features
Proceedings of International Joint Conference on Neural Networks, San Jose, California, USA, July 31 August 5, 2011 A Hubel Wiesel Model of Early Concept Generalization Based on Local Correlation of Input
Original citation: Robinson, Leigh and Rolls, Edmund T.. (25) Invariant visual object recognition : biologically plausible approaches. Biological Cybernetics, 9 (4-5). pp. 55-535. 658. Permanent WRAP url:
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
THE ENCODING OF PARTS AND WHOLES
THE ENCODING OF PARTS AND WHOLES IN THE VISUAL CORTICAL HIERARCHY JOHAN WAGEMANS LABORATORY OF EXPERIMENTAL PSYCHOLOGY UNIVERSITY OF LEUVEN, BELGIUM DIPARTIMENTO DI PSICOLOGIA, UNIVERSITÀ DI MILANO-BICOCCA,
Goals. Visual behavior jobs of vision. The visual system: overview of a large-scale neural architecture. kersten.org
The visual system: overview of a large-scale neural architecture Daniel Kersten Computational Vision Lab Psychology Department, U. Minnesota Goals Provide an overview of a major brain subsystem to help
LISC-322 Neuroscience Cortical Organization
LISC-322 Neuroscience Cortical Organization THE VISUAL SYSTEM Higher Visual Processing Martin Paré Assistant Professor Physiology & Psychology Most of the cortex that covers the cerebral hemispheres is
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,
Bottom-up and top-down processing in visual perception
Bottom-up and top-down processing in visual perception Thomas Serre Brown University Department of Cognitive & Linguistic Sciences Brown Institute for Brain Science Center for Vision Research The what
EDGE DETECTION. Edge Detectors. ICS 280: Visual Perception
EDGE DETECTION Edge Detectors Slide 2 Convolution & Feature Detection Slide 3 Finds the slope First derivative Direction dependent Need many edge detectors for all orientation Second order derivatives
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
arxiv: v2 [cs.cv] 19 Dec 2017
![arxiv: v2 [cs.cv] 19 Dec 2017](/thumbs/89/97557782.jpg "arxiv: v2 [cs.cv] 19 Dec 2017")
An Ensemble of Deep Convolutional Neural Networks for Alzheimer s Disease Detection and Classification arxiv:1712.01675v2 [cs.cv] 19 Dec 2017 Jyoti Islam Department of Computer Science Georgia State University
Invariant Pattern Recognition using Bayesian Inference on Hierarchical Sequences
Invariant Pattern Recognition using Bayesian Inference on Hierarchical Sequences Dileep George Electrical Engineering, Stanford University and Redwood Neuroscience Institute Menlo Park, CA 94025 dil@stanford.edu
Early Stages of Vision Might Explain Data to Information Transformation
Early Stages of Vision Might Explain Data to Information Transformation Baran Çürüklü Department of Computer Science and Engineering Mälardalen University Västerås S-721 23, Sweden Abstract. In this paper
Prof. Greg Francis 7/31/15
s PSY 200 Greg Francis Lecture 06 How do you recognize your grandmother? Action potential With enough excitatory input, a cell produces an action potential that sends a signal down its axon to other cells
COGS 101A: Sensation and Perception
COGS 101A: Sensation and Perception 1 Virginia R. de Sa Department of Cognitive Science UCSD Lecture 5: LGN and V1: Magno and Parvo streams Chapter 3 Course Information 2 Class web page: http://cogsci.ucsd.edu/
How Does Our Visual System Achieve Shift and Size Invariance?
In J. L. Van Hemmen and T. J. Sejnowski (Eds.), Problems in Systems Neuroscience, Oxford University Press (2002) (to appear) How Does Our Visual System Achieve Shift and Size Invariance? Laurenz Wiskott
The Eye. Cognitive Neuroscience of Language. Today s goals. 5 From eye to brain. Today s reading
Cognitive Neuroscience of Language 5 From eye to brain Today s goals Look at the pathways that conduct the visual information from the eye to the visual cortex Marielle Lange http://homepages.inf.ed.ac.uk/mlange/teaching/cnl/
Position invariant recognition in the visual system with cluttered environments
PERGAMON Neural Networks 13 (2000) 305 315 Contributed article Position invariant recognition in the visual system with cluttered environments S.M. Stringer, E.T. Rolls* Oxford University, Department of
How Does Our Visual System Achieve Shift and Size Invariance?
To appear in J. L. van Hemmen and T. J. Sejnowski (Eds.), Problems in Systems Neuroscience, Oxford University Press (2004). Submitted and accepted for publication January 2001. Also: Cognitive Sciences
Nonlinear processing in LGN neurons
Nonlinear processing in LGN neurons Vincent Bonin *, Valerio Mante and Matteo Carandini Smith-Kettlewell Eye Research Institute 2318 Fillmore Street San Francisco, CA 94115, USA Institute of Neuroinformatics
A Neurally-Inspired Model for Detecting and Localizing Simple Motion Patterns in Image Sequences
A Neurally-Inspired Model for Detecting and Localizing Simple Motion Patterns in Image Sequences Marc Pomplun 1, Yueju Liu 2, Julio Martinez-Trujillo 2, Evgueni Simine 2, and John K. Tsotsos 2 1 Department
Plasticity of Cerebral Cortex in Development
Plasticity of Cerebral Cortex in Development Jessica R. Newton and Mriganka Sur Department of Brain & Cognitive Sciences Picower Center for Learning & Memory Massachusetts Institute of Technology Cambridge,
Sparse Coding in Sparse Winner Networks
Sparse Coding in Sparse Winner Networks Janusz A. Starzyk 1, Yinyin Liu 1, David Vogel 2 1 School of Electrical Engineering & Computer Science Ohio University, Athens, OH 45701 {starzyk, yliu}@bobcat.ent.ohiou.edu
Stephen Grossberg, Jeffrey Markowitz, and Yongqiang Cao
i On the Road to Invariant Recognition: Explaining Tradeoff and Morph Properties of Cells in Inferotemporal Cortex using Multiple-Scale Task-Sensitive Attentive Learning Stephen Grossberg, Jeffrey Markowitz,
2/3/17. Visual System I. I. Eye, color space, adaptation II. Receptive fields and lateral inhibition III. Thalamus and primary visual cortex
1 Visual System I I. Eye, color space, adaptation II. Receptive fields and lateral inhibition III. Thalamus and primary visual cortex 2 1 2/3/17 Window of the Soul 3 Information Flow: From Photoreceptors
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
CS-E Deep Learning Session 4: Convolutional Networks
CS-E4050 - Deep Learning Session 4: Convolutional Networks Jyri Kivinen Aalto University 23 September 2015 Credits: Thanks to Tapani Raiko for slides material. CS-E4050 - Deep Learning Session 4: Convolutional
arxiv: v1 [q-bio.nc] 12 Jun 2014
![arxiv: v1 [q-bio.nc] 12 Jun 2014](/thumbs/89/97809042.jpg "arxiv: v1 [q-bio.nc] 12 Jun 2014")
1 arxiv:1406.3284v1 [q-bio.nc] 12 Jun 2014 Deep Neural Networks Rival the Representation of Primate IT Cortex for Core Visual Object Recognition Charles F. Cadieu 1,, Ha Hong 1,2, Daniel L. K. Yamins 1,
Cell Responses in V4 Sparse Distributed Representation
Part 4B: Real Neurons Functions of Layers Input layer 4 from sensation or other areas 3. Neocortical Dynamics Hidden layers 2 & 3 Output layers 5 & 6 to motor systems or other areas 1 2 Hierarchical Categorical
Introduction to Computational Neuroscience
Introduction to Computational Neuroscience Lecture 7: Network models Lesson Title 1 Introduction 2 Structure and Function of the NS 3 Windows to the Brain 4 Data analysis 5 Data analysis II 6 Single neuron
A Bayesian inference theory of attention: neuroscience and algorithms Sharat Chikkerur, Thomas Serre, and Tomaso Poggio
Computer Science and Artificial Intelligence Laboratory Technical Report MIT-CSAIL-TR-29-47 CBCL-28 October 3, 29 A Bayesian inference theory of attention: neuroscience and algorithms Sharat Chikkerur,
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,
From feedforward vision to natural vision: The impact of free viewing and clutter on monkey inferior temporal object representations
From feedforward vision to natural vision: The impact of free viewing and clutter on monkey inferior temporal object representations James DiCarlo The McGovern Institute for Brain Research Department of
1 Perception& Attention. 5 The Retina. 3 Overview of the Visual System. 6 LGN of the Thalamus. 4 Two Streams: Ventral what vs.
1 Perception& Attention Perception is effortless but its underlying mechanisms are incredibly sophisticated. Biology of the visual system Representations in primary visual cortex and Hebbian learning Object
Recurrent Refinement for Visual Saliency Estimation in Surveillance Scenarios
2012 Ninth Conference on Computer and Robot Vision Recurrent Refinement for Visual Saliency Estimation in Surveillance Scenarios Neil D. B. Bruce*, Xun Shi*, and John K. Tsotsos Department of Computer
Identify these objects
Pattern Recognition The Amazing Flexibility of Human PR. What is PR and What Problems does it Solve? Three Heuristic Distinctions for Understanding PR. Top-down vs. Bottom-up Processing. Semantic Priming.
The Visual System s Internal Model of the World
INVITED PAPER The Visual System s Internal Model of the World Perceptual computation can be usefully viewed through Bayesian inferencing. Perception follows as a statistical inference based on an internal
Evaluation of a Shape-Based Model of Human Face Discrimination Using fmri and Behavioral Techniques
Neuron 50, 159 172, April 6, 2006 ª2006 Elsevier Inc. DOI 10.1016/j.neuron.2006.03.012 Evaluation of a Shape-Based Model of Human Face Discrimination Using fmri and Behavioral Techniques Xiong Jiang, 1
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
Neuronal responses to plaids
Vision Research 39 (1999) 2151 2156 Neuronal responses to plaids Bernt Christian Skottun * Skottun Research, 273 Mather Street, Piedmont, CA 94611-5154, USA Received 30 June 1998; received in revised form
Deep Neural Networks: A New Framework for Modeling Biological Vision and Brain Information Processing
ANNUAL REVIEWS Further Click here to view this article's online features: Download figures as PPT slides Navigate linked references Download citations Explore related articles Search keywords Annu. Rev.
Gabriel Kreiman Children s Hospital, Harvard Medical School
Neural computa-ons: lessons from peeking inside the brain Gabriel Kreiman Children s Hospital, Harvard Medical School gabriel.kreiman@tch.harvard.edu hcp://klab.tch.harvard.edu What computers can do [2014]
M Cells. Why parallel pathways? P Cells. Where from the retina? Cortical visual processing. Announcements. Main visual pathway from retina to V1
Announcements exam 1 this Thursday! review session: Wednesday, 5:00-6:30pm, Meliora 203 Bryce s office hours: Wednesday, 3:30-5:30pm, Gleason https://www.youtube.com/watch?v=zdw7pvgz0um M Cells M cells
OPTO 5320 VISION SCIENCE I
OPTO 5320 VISION SCIENCE I Monocular Sensory Processes of Vision: Color Vision Mechanisms of Color Processing . Neural Mechanisms of Color Processing A. Parallel processing - M- & P- pathways B. Second
An Introduction to Biologically-Inspired Visual Recognition
Universität Hamburg Department Informatik Knowledge Technology, WTM An Introduction to Biologically-Inspired Visual Recognition Seminar Paper Biologically-Inspired Artificial Intelligence Sebastian Starke
Chapter 5: Perceiving Objects and Scenes
Chapter 5: Perceiving Objects and Scenes The Puzzle of Object and Scene Perception The stimulus on the receptors is ambiguous. Inverse projection problem: An image on the retina can be caused by an infinite
A quantitative theory of immediate visual recognition
A quantitative theory of immediate visual recognition Thomas Serre, Gabriel Kreiman, Minjoon Kouh, Charles Cadieu, Ulf Knoblich and Tomaso Poggio Center for Biological and Computational Learning McGovern
COGS 101A: Sensation and Perception
COGS 101A: Sensation and Perception 1 Virginia R. de Sa Department of Cognitive Science UCSD Lecture 6: Beyond V1 - Extrastriate cortex Chapter 4 Course Information 2 Class web page: http://cogsci.ucsd.edu/
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
arxiv: v1 [stat.ml] 23 Jan 2017
![arxiv: v1 [stat.ml] 23 Jan 2017](/thumbs/81/83414183.jpg "arxiv: v1 [stat.ml] 23 Jan 2017")
Learning what to look in chest X-rays with a recurrent visual attention model arxiv:1701.06452v1 [stat.ml] 23 Jan 2017 Petros-Pavlos Ypsilantis Department of Biomedical Engineering King s College London
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
Competing Frameworks in Perception
Competing Frameworks in Perception Lesson II: Perception module 08 Perception.08. 1 Views on perception Perception as a cascade of information processing stages From sensation to percept Template vs. feature
Competing Frameworks in Perception
Competing Frameworks in Perception Lesson II: Perception module 08 Perception.08. 1 Views on perception Perception as a cascade of information processing stages From sensation to percept Template vs. feature
Canonical Cortical Circuits
2 Canonical Cortical Circuits Rodney J. Douglas and Kevan A. C. Martin The observation that neural circuits of the neocortex are adapted to many different tasks raises deep questions of how they are organized
arxiv: v3 [stat.ml] 28 Oct 2017
![arxiv: v3 [stat.ml] 28 Oct 2017](/thumbs/81/83820195.jpg "arxiv: v3 [stat.ml] 28 Oct 2017")
Interpretable Deep Learning applied to Plant Stress Phenotyping arxiv:1710.08619v3 [stat.ml] 28 Oct 2017 Sambuddha Ghosal sghosal@iastate.edu Asheesh K. Singh singhak@iastate.edu Arti Singh arti@iastate.edu
Biologically Motivated Local Contextual Modulation Improves Low-Level Visual Feature Representations
Biologically Motivated Local Contextual Modulation Improves Low-Level Visual Feature Representations Xun Shi,NeilD.B.Bruce, and John K. Tsotsos Department of Computer Science & Engineering, and Centre
Computational Principles of Cortical Representation and Development
Computational Principles of Cortical Representation and Development Daniel Yamins In making sense of the world, brains actively reformat noisy and complex incoming sensory data to better serve the organism
Elias B Issa, PhD. Curriculum Vitae 08/2016. RESEARCH INTEREST The neural mechanisms and computational principles underlying high-level vision
Elias B Issa, PhD Curriculum Vitae 08/2016 Massachusetts Institute of Technology 77 Massachusetts Ave, 46-6157 Cambridge, MA 02139 Office / 617.324.0306 Cell / 443.310.5896 Email / issa@mit.edu RESEARCH
Overview of the visual cortex. Ventral pathway. Overview of the visual cortex
Overview of the visual cortex Two streams: Ventral What : V1,V2, V4, IT, form recognition and object representation Dorsal Where : V1,V2, MT, MST, LIP, VIP, 7a: motion, location, control of eyes and arms
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