Topological Neural Networks Bear, Connors & Paradiso (2001). Neuroscience: Exploring The Brain. Pg. 474.

Slides:



Advertisements
Similar presentations
© Negnevitsky, Pearson Education, Introduction Introduction Hebbian learning Hebbian learning Generalised Hebbian learning algorithm Generalised.
Advertisements

Bioinspired Computing Lecture 14
Chapter 2.
Neural Networks Dr. Peter Phillips. The Human Brain (Recap of week 1)
Un Supervised Learning & Self Organizing Maps. Un Supervised Competitive Learning In Hebbian networks, all neurons can fire at the same time Competitive.
Neural Networks Chapter 9 Joost N. Kok Universiteit Leiden.
Unsupervised learning. Summary from last week We explained what local minima are, and described ways of escaping them. We investigated how the backpropagation.
Self Organization: Competitive Learning
5/16/2015Intelligent Systems and Soft Computing1 Introduction Introduction Hebbian learning Hebbian learning Generalised Hebbian learning algorithm Generalised.
Kohonen Self Organising Maps Michael J. Watts
Unsupervised Learning with Artificial Neural Networks The ANN is given a set of patterns, P, from space, S, but little/no information about their classification,
Artificial neural networks:
Competitive learning College voor cursus Connectionistische modellen M Meeter.
Unsupervised Networks Closely related to clustering Do not require target outputs for each input vector in the training data Inputs are connected to a.
cells in cochlear nucleus
Lesions of Retinostriate Pathway Lesions (usually due to stroke) cause a region of blindness called a scotoma Identified using perimetry note macular sparing.
X0 xn w0 wn o Threshold units SOM.
2002/01/21PSCY , Term 2, Copyright Jason Harrison, The Brain from retina to extrastriate cortex.
Writing Workshop Find the relevant literature –Use the review journals as a first approach e.g. Nature Reviews Neuroscience Trends in Neuroscience Trends.
Slides are based on Negnevitsky, Pearson Education, Lecture 8 Artificial neural networks: Unsupervised learning n Introduction n Hebbian learning.
1 Chapter 11 Neural Networks. 2 Chapter 11 Contents (1) l Biological Neurons l Artificial Neurons l Perceptrons l Multilayer Neural Networks l Backpropagation.
Structure and function
Instar Learning Law Adapted from lecture notes of the course CN510: Cognitive and Neural Modeling offered in the Department of Cognitive and Neural Systems.
November 24, 2009Introduction to Cognitive Science Lecture 21: Self-Organizing Maps 1 Self-Organizing Maps (Kohonen Maps) In the BPN, we used supervised.
Un Supervised Learning & Self Organizing Maps Learning From Examples
Neural Networks Lecture 17: Self-Organizing Maps
Lecture 09 Clustering-based Learning
Copyright © 2007 Wolters Kluwer Health | Lippincott Williams & Wilkins Neuroscience: Exploring the Brain, 3e Chapter 10: The Central Visual System.
Hearing Part 2. Tuning Curve Sensitivity of a single sensory neuron to a particular frequency of sound Two mechanisms for fine tuning of sensory neurons,
Lecture 12 Self-organizing maps of Kohonen RBF-networks
KOHONEN SELF ORGANISING MAP SEMINAR BY M.V.MAHENDRAN., Reg no: III SEM, M.E., Control And Instrumentation Engg.
TEMPLATE DESIGN © A Computational Model of Auditory Processing for Sound Localization Diana Stan, Michael Reed Department.
Self Organized Map (SOM)
CZ5225: Modeling and Simulation in Biology Lecture 5: Clustering Analysis for Microarray Data III Prof. Chen Yu Zong Tel:
Artificial Neural Networks Dr. Abdul Basit Siddiqui Assistant Professor FURC.
Artificial Neural Network Unsupervised Learning
Critical periods in development - “nature” vs. “nurture”
1 Computational Vision CSCI 363, Fall 2012 Lecture 3 Neurons Central Visual Pathways See Reading Assignment on "Assignments page"
NEURAL NETWORKS FOR DATA MINING
THE VISUAL SYSTEM: EYE TO CORTEX Outline 1. The Eyes a. Structure b. Accommodation c. Binocular Disparity 2. The Retina a. Structure b. Completion c. Cone.
Slide 1 Neuroscience: Exploring the Brain, 3rd Ed, Bear, Connors, and Paradiso Copyright © 2007 Lippincott Williams & Wilkins Bear: Neuroscience: Exploring.
Auditory transduction Figure by MIT OCW. After figure in: Bear, Mark F., Barry W. Connors, and Michael A. Paradiso. Neuroscience: Exploring the Brain.
1 Chapter 11 Neural Networks. 2 Chapter 11 Contents (1) l Biological Neurons l Artificial Neurons l Perceptrons l Multilayer Neural Networks l Backpropagation.
Machine Learning Neural Networks (3). Understanding Supervised and Unsupervised Learning.
Self Organizing Feature Map CS570 인공지능 이대성 Computer Science KAIST.
UNSUPERVISED LEARNING NETWORKS
381 Self Organization Map Learning without Examples.
Semiconductors, BP&A Planning, DREAM PLAN IDEA IMPLEMENTATION.
Fast Learning in Networks of Locally-Tuned Processing Units John Moody and Christian J. Darken Yale Computer Science Neural Computation 1, (1989)
Self-Organizing Maps (SOM) (§ 5.5)
Self Organizing Maps: Clustering With unsupervised learning there is no instruction and the network is left to cluster patterns. All of the patterns within.
CHAPTER 14 Competitive Networks Ming-Feng Yeh.
Outline Of Today’s Discussion 1.LGN Projections & Color Opponency 2.Primary Visual Cortex: Structure 3.Primary Visual Cortex: Individual Cells.
A Self-organizing Semantic Map for Information Retrieval Xia Lin, Dagobert Soergel, Gary Marchionini presented by Yi-Ting.
Computational Intelligence: Methods and Applications Lecture 9 Self-Organized Mappings Włodzisław Duch Dept. of Informatics, UMK Google: W Duch.
Self-Organizing Network Model (SOM) Session 11
Data Mining, Neural Network and Genetic Programming
Unsupervised Learning and Neural Networks
Lecture 22 Clustering (3).
Kohonen Self-organizing Feature Maps
Neural Networks and Their Application in the Fields of Coporate Finance By Eric Séverin Hanna Viinikainen.
Computational Intelligence: Methods and Applications
Self-Organizing Maps (SOM) (§ 5.5)
Self Organizing Maps A major principle of organization is the topographic map, i.e. groups of adjacent neurons process information from neighboring parts.
Feature mapping: Self-organizing Maps
The Network Approach: Mind as a Web
Artificial Neural Networks
Unsupervised Networks Closely related to clustering
Presentation transcript:

Topological Neural Networks Bear, Connors & Paradiso (2001). Neuroscience: Exploring The Brain. Pg. 474.

Self-Organizing Maps SOMs = Competitive Networks where: –1 input and 1 output layer. –All input nodes feed into all output nodes. –Output layer nodes are NOT a clique. Each node has a few neighbors. –On each training input, all output nodes that are within a topological distance, d T, of D from the winner node will have their incoming weights modified. d T (y i,y j ) = # nodes that must be traversed in the output layer in moving between output nodes y i and y j. –D is typically decreased as training proceeds. Fully Interconnected Input Output Partially Intraconnected

There Goes The Neighborhood D = 1 D = 2 D = 3 As the training period progresses, gradually decrease D. Over time, islands form in which the center represents the centroid C of a set of input vectors, S, while nearby neighbors represent slight variations on C and more distant neighbors are major variations. These neighbors may only win on a few (or no) input vectors, while the island center will win on many of the elements of S.

Self Organization In the beginning, the Euclidian distance d E (y l,y k ) and Topological distance d T (y l,y k ) between output nodes y l and y k will not be related. But during the course of training, they will become positively correlated: Neighbor nodes in the topology will have similar weight vectors, and topologically distant nodes will have very different weight vectors. Euclidean Neighbor Emergent Structure of Output Layer BeforeAfter Topological Neighbor

Self-Organized Maps for Robot Navigation Owen & Nehmzow (1998) Task: Autonomous robot navigation in a laboratory Goals: 1. Find a useful internal representation (i.e. map) that supports an intelligent choice of actions for the given sensory inputs 2. Let the robot build/learn the map itself - Saves the user from specifying it. - Allows the robot to handle new environments. - By learning the map in a noisy, real-world situation, the robot will be more apt to handle other noisy environments. Approach: Use an SOM to organize situation-action vectors. The emerging structure of the SOM then constitutes the robot’s functional internal representation of both the outside world and the appropriate actions to take in different regions of that world.

The Training Phase R 1. Record Sensory Info “Turn Right & Slow Down 2. Get correct actions 3. Input Vector = Sensory Inputs & Actions Input Output 4. Run SOM on Input Vector 5. Update Winner & Neighbors

The Testing Phase R 1. Record Sensory Info 2. Input Vector = Sensory Inputs & No Actions Input Output 3. Run SOM on Input Vector 4. Read Recommended Actions from the Winner’s Weight Vector A

Clustering of Perceptual Signatures The general closeness of successive winners shows a correlation between points & distances in the objective world and the robot’s functional view of that world. Note: A trace of the robot’s path on a map of the real world (i.e. lab floor) would have ONLY short moves. The sequence of winner nodes during the testing phase of a typical navigation task.

SOM for Navigation Summary SOM Regions = Perceptual Landmarks = Sets of similar perceptual patterns Navigation = Association of actions with perceptual landmarks Behavior is controlled by the robot’s subjective functional interpretation of the world, which may abstract the world into a few key perceptual categories. No extensive objective map of the entire environment is required. Useful maps are user & task centered. Robustness (Fault Tolerance): The robot also navigates successfully when a few of its sensors are damaged => The SOM has generalized from the specific training instances. Similar neuronal organizations, with correlations between points in the visual field and neurons in a brain region, are found in many animals.

Brain Maps

Tonotopic Maps in the Auditory System Spiral Ganglion Ventral Cochlear Nucleus Superior Olive Inferior Colliculus MGN Auditory Cortex Cochlea (Inner Ear) 20 kHz 4 kHz 1 kHz 10 kHz Cochlea Sp. Gang. Cochlear Nucleus Source Localization Via Delay Lines 20 kHz4 kHz1 kHz10 kHz Tonotopy preserved through all 7 levels of processing

Source Localization using Delay Lines Source Location Detection Neurons: Need 2 simultaneous inputs to fire Transformer Neurons: Convert sound frequency into a neural firing pattern, which is phase-locked to the sound waves (although lower freq). Right Ear Left Ear Left 90 o Left 45 o Right 90 o Right 45 o Straight Ahead! Owls have different ear heights, so they can use the same mechanism for horizontal and vertical localization Topological Map = Similar dirs detected by neighboring cells.

Occular Dominance & Orientation Columns Right eyeLeft eyeRight eyeLeft eye Layers 5 & 6 of V1 Neural Response (Firing rate) 0o0o 90 o -90 o 2 Topological Maps Cells respond to lines at particular angles, and nearby cells respond to similar angles. Regions of cells respond to the same eye. Retina LGN Orientation Angle

Self-Organizing Maps of Orientation Columns Training Patterns Retina Visual Cortex Each VC cell gets input from all retinal cells. Initially, all weights random. Each pattern is presented, and the ”winning” VC cell gets to change its weights to better match the input. Nearby cells in a slowly- shrinking neighborhood also update their weights.

Emerging Orientation Preferences Many VC cells show a strong preference for a particular orientation. Neighboring cells show similar preferences. Gradients of preferred orientations often form along vertical, horizontal and diagonal axes.

Biological Kohonen Maps The orientation columns clearly emerge from a Kohonen algorithm of weight- change spreading in a slowly-shrinking neighborhood. But this lacks biological realism. So classic Kohonen maps cannot explain the formation of orientation columns. However, the basic neurophysiological mechanisms of late-stage long-term potentiation (late LTP) can be used in a modified Kohonen map to produce similar orientation-columns. Key idea: When a pre-synaptic (retinal) node R and post-synaptic (VC) node V both fire, then: – the RV weight should be increased, –R should produce more axons, some of which will spread to OTHER post- synaptic nodes, V2,V3..in the general neighborhood of V. So each training pattern will produce a winner node, V, and portions of the input weights to V will be randomly distributed to the input weights of some neighboring VC nodes: Weight(R,V) will affect Weight(R,V2), Weight(R,V3), etc. Extent of random neighborhoods gradually decreases (just as the degree of plasticity decreases during biological development)

Winner VC node R Random neighbor Retina Visual Cortex