CLS, Rapid Schema Consistent Learning, and Similarity-weighted Interleaved learning Psychology 209 Feb 26, 2019.

Slides:



Advertisements
Similar presentations
Distributed Representation, Connection-Based Learning, and Memory Psychology 209 February 1, 2013.
Advertisements

Learning and Memory in Hippocampus and Neocortex: A Complementary Learning Systems Approach Psychology 209 Feb 11, 2014.
Does the Brain Use Symbols or Distributed Representations? James L. McClelland Department of Psychology and Center for Mind, Brain, and Computation Stanford.
Emergence in Cognitive Science: Semantic Cognition Jay McClelland Stanford University.
Memory Systems Chapter 23 Friday, December 5, 2003.
Introduction to Psychology Suzy Scherf Lecture 9: How Do We Know? Memory.
Cooperation of Complementary Learning Systems in Memory Review and Update on the Complementary Learning Systems Framework James L. McClelland Psychology.
General Knowledge Dr. Claudia J. Stanny EXP 4507 Memory & Cognition Spring 2009.
Development and Disintegration of Conceptual Knowledge: A Parallel-Distributed Processing Approach Jay McClelland Department of Psychology and Center for.
Dynamics of learning: A case study Jay McClelland Stanford University.
Learning, memory & amnesia
Using Backprop to Understand Apects of Cognitive Development PDP Class Feb 8, 2010.
Representation, Development and Disintegration of Conceptual Knowledge: A Parallel-Distributed Processing Approach James L. McClelland Department of Psychology.
Integrating New Findings into the Complementary Learning Systems Theory of Memory Jay McClelland, Stanford University.
Disintegration of Conceptual Knowledge In Semantic Dementia James L. McClelland Department of Psychology and Center for Mind, Brain, and Computation Stanford.
The Brain Basis of Memory: Theory and Data James L. McClelland Stanford University.
Human Cognitive Processes: psyc 345 Ch. 6 Long-term memory Takashi Yamauchi © Takashi Yamauchi (Dept. of Psychology, Texas A&M University)
Introduction to Psychology: Memory Cleoputri Yusainy, PhD.
Contrasting Approaches To Semantic Knowledge Representation and Inference Psychology 209 February 15, 2013.
MULTIPLE MEMORY SYSTEM IN HUMANS
Emergence of Semantic Knowledge from Experience Jay McClelland Stanford University.
The Influence of Feature Type, Feature Structure and Psycholinguistic Parameters on the Naming Performance of Semantic Dementia and Alzheimer’s Patients.
Development, Disintegration, and Neural Basis of Semantic Cognition: A Parallel-Distributed Processing Approach James L. McClelland Department of Psychology.
Similarity and Attribution Contrasting Approaches To Semantic Knowledge Representation and Inference Jay McClelland Stanford University.
Learning and Memory in Hippocampus and Neocortex: A Complementary Learning Systems Approach Psychology 209 Feb 11&13, 2013.
Rapid integration of new schema- consistent information in the Complementary Learning Systems Theory Jay McClelland, Stanford University.
Semantic Cognition: A Parallel Distributed Processing Approach James L. McClelland Center for the Neural Basis of Cognition and Departments of Psychology.
Last Lecture Frontal Lobe Anatomy Inhibition and voluntary control
The Emergent Structure of Semantic Knowledge
Memory: Its Nature and Organization in the Brain James L. McClelland Stanford University.
Emergent Semantics: Meaning and Metaphor Jay McClelland Department of Psychology and Center for Mind, Brain, and Computation Stanford University.
Semantic Knowledge: Its Nature, its Development, and its Neural Basis James L. McClelland Department of Psychology and Center for Mind, Brain, and Computation.
The Neuropsychology of Memory Ch. 11. Outline Case studies Korsakoff’s Amnesia Alzheimer’s Disease Posttraumatic Amnesia Clive Wearing video Theories.
Development and Disintegration of Conceptual Knowledge: A Parallel-Distributed Processing Approach James L. McClelland Department of Psychology and Center.
Long Term Memory LONG TERM MEMORY (LTM)  Variety of information stored in LTM:  The capital of Turkey  How to drive a car.
Chapter 7 Memory. Objectives 7.1 Overview: What Is Memory? Explain how human memory differs from an objective video recording of events. 7.2 Constructing.
Chapter 9 Knowledge. Some Questions to Consider Why is it difficult to decide if a particular object belongs to a particular category, such as “chair,”
Memory: An Introduction
Complementary Learning Systems
Psychology 209 – Winter 2017 January 31, 2017
What is cognitive psychology?
December 9, 2016 Objective: Journal:
Human MEMORY.
Cognitive Processes in SLL and Bilinguals:
Simple recurrent networks.
Psychology 209 – Winter 2017 Feb 28, 2017
Neurobiology of Learning and Memory
Storing and Retrieving Memories
Neural Networks.
LEARNING & MEMORY Jaan Aru
Development and Disintegration of Conceptual Knowledge: A Parallel-Distributed Processing Approach James L. McClelland Department of Psychology and Center.
NATURE NEUROSCIENCE 2007 Coordinated memory replay in the visual cortex and hippocampus during sleep Daoyun Ji & Matthew A Wilson Department of Brain.
Does the Brain Use Symbols or Distributed Representations?
Cooperation of Complementary Learning Systems in Memory
Memory and Learning: Their Nature and Organization in the Brain
Emergence of Semantic Structure from Experience
Emergence of Semantics from Experience
Class Schedule In-text Citations Long-term Memory: Organization
Cognitive Approach Short-term memory – a limited amount of processing takes place here. Short term memory has a very limited capacity (7 items +/- 2)
Cognitive Processes PSY 334
ESSENTIALS OF PSYCHOLOGY
The ability to store and retrieve information over time.
Types of LTM.
Intact Memory for Irrelevant Information Impairs Perception in Amnesia
Chapter 7: Memory.
Interplay of Hippocampus and Prefrontal Cortex in Memory
Toward a Great Class Project: Discussion of Stoianov & Zorzi’s Numerosity Model Psych 209 – 2019 Feb 14, 2019.
The Network Approach: Mind as a Web
thinking about learning and memory
Presentation transcript:

CLS, Rapid Schema Consistent Learning, and Similarity-weighted Interleaved learning Psychology 209 Feb 26, 2019

Your knowledge is in your connections! An experience is a pattern of activation over neurons in one or more brain regions. The trace left in memory is the set of adjustments to the strengths of the connections. Each experience leaves such a trace, but the traces are not separable or distinct. Rather, they are superimposed in the same set of connection weights. Recall involves the recreation of a pattern of activation, using a part or associate of it as a cue. The reinstatement depends on the knowledge in the connection weights, which in general will reflect influences of many different experiences. Thus, memory is always a constructive process, dependent on contributions from many different experiences.

Effect of a Hippocampal Lesion Intact performance on tests of intelligence, general knowledge, language, other acquired skills Dramatic deficits in formation of some types of new memories: Explicit memories for episodes and events Paired associate learning Arbitrary new factual information Spared priming and skill acquisition Temporally graded retrograde amnesia: lesion impairs recent memories leaving remote memories intact. Note: HM’s lesion was bilateral

Key Points We learn about the general pattern of experiences, not just specific things Gradual learning in the cortex builds implicit semantic and procedural knowledge that forms much of the basis of our cognitive abilities The Hippocampal system complements the cortex by allowing us to learn specific things without interference with existing structured knowledge In general these systems must be thought of as working together rather than being alternative sources of information. Much of behavior and cognition depends on both specific and general knowledge

Emergence of Meaning in Learned Distributed Representations through Gradual Interleaved Learning Distributed representations (what ML calls embeddings) that capture aspects of meaning emerge through a gradual learning process The progression of learning and the representations formed capture many aspects of cognitive development Progressive differentiation Sensitivity to coherent covariation across contexts Reorganization of conceptual knowledge

The Rumelhart Model

The Training Data: All propositions true of items at the bottom level of the tree, e.g.: Robin can {grow, move, fly}

Early Later Later Still E x p e r i e n c e

What happens in this system if we try to learn something new? Such as a Penguin

Learning Something New Used network already trained with eight items and their properties. Added one new input unit fully connected to the representation layer Trained the network with the following pairs of items: penguin-isa living thing-animal-bird penguin-can grow-move-swim

Rapid Learning Leads to Catastrophic Interference

Avoiding Catastrophic Interference with Interleaved Learning

Rapid Consolidation of Schema Consistent Information Richard Morris Rapid Consolidation of Schema Consistent Information

Tse et al (Science, 2007, 2011) During training, 2 wells uncovered on each trial

Schemata and Schema Consistent Information What is a ‘schema’? An organized knowledge structure into which existing knowledge is organized. What is schema consistent information? Information that can be added to a schema without disturbing it. What about a penguin? Partially consistent Partially inconsistent In contrast, consider a trout a cardinal

New Simulations Initial training with eight items and their properties as before. Added one new input unit fully connected to the representation layer also as before Trained the network on one of the following pairs of items: penguin-isa & penguin-can trout-isa & trout-can cardinal-isa & cardinal-can

New Learning of Consistent and Partially Inconsistent Information INTERFERENCE

Connection Weight Changes after Simulated NPA, OPA and NM Analogs Tse et al. 2011

How Does It Work?

How Does It Work?

Remaining Questions Are all aspects of new learning integrated into cortex-like networks at the same rate? No, some aspects are integrated much more slowly than others Is it possible to avoid replaying everything one already knows when one wants to learn new things with arbitrary structure? Yes, at least in some circumstances that we will explore Perhaps the answers to these questions will allow us to make more efficient use of both cortical and hippocampal resources for learning.

Toward an Explicit Mathematical Theory of Interleaved Learning Characterizing structure in a dataset to be learned The deep linear network that can learn this structure The dynamics of learning the structure in the dataset Initial learning of a base data set Subsequent learning of an additional item Using similarity weighted interleaved learning to increase efficiency of interleaved learning Initial thoughts on how we might use the hippocampus more efficiently

Hierarchical structure in a synthetic data set Sparrow Hawk Salmon Sunfish Oak Maple Rose Daisy SparrowHawk

Processing and Learning in a deep linear network Saxe et al, (2013a,b,…)

SVD of the dataset

Dynamics of Learning – one-hot inputs SSE a(t) Variable discrepancy affects takeoff point, but not shape Solid lines are simulated values of a(t) Dashed lines are based on the equation

Dynamics of Learning – auto-associator SSE 𝑠 2 a(t) 𝑠 2 Dynamics are a bit more predictable Solid lines are simulated values of a(t) Dashed lines are based on the equation

Adding a new member of an existing category Sparrow Hawk Salmon Sunfish Oak Maple Rose Daisy SparrowHawk

SVD of New Complete Dataset

The consequence of standard interleaved learning

SVD Analysis of Network Output for Birds Adjusted Dimensions New Dimension

Similarity Weighted Interleaved Learning Full Interleaving Similarity- weighted Interleaving Uniform Interleaving

Freezing the output weights initially Full Interleaving Similarity- weighted Interleaving Uniform Interleaving

Discussion Integration of fine-grained structure into a deep network may always be a slow process Sometimes this fine-grained structure is ultimately fairly arbitrary and idiosyncratic, although other times it may be part of a deeper pattern the learner has not previously seen One way to address such integration: Initial reliance on sparse / item-specific representation This could be made more efficient by storing only the ‘correction vector’ in the hippocampus Gradual integration through interleaved learning

SparrowHawk Error Vector After Easy Integration Phase is Complete

Questions, answers and next steps Are all aspects of new learning integrated into cortex-like networks at the same rate? No, some aspects are integrated much more slowly than others Is it possible to avoid replaying everything one already knows when one wants to learn new things with arbitrary structure? Yes, at least in some circumstances that we have explored Perhaps the answers to these questions will allow us to make more efficient use of both cortical and hippocampal resources for learning.