White Blue and Lightnings - ut

White Blue and Lightnings - ut

LEARNING & MEMORY Jaan Aru [email protected]

Deep neural nets Learning through weight changes

Feedback connections! But the biggest difference?

The most famous patient: H.M. Hippocampus Medial temporal lobe

Patient H.M. Types of memory

MEMENTO Patient H.M. demonstrates that ...

1) medial temporal lobe is important for memory 2) but it is not necessary for all memory! 3) there is a difference between short-term and long term memory

4) there is a difference between declarative and procedural memory 5) medial temporal lobe is necessary for long term declarative memory

Taxonomy of long-term memory complementary learning systems (CLS)

intelligent agents must possess two learning systems neocortex and hippocampus (MTL) NC gradually acquires structured knowledge

HC quickly learns the specifics of individual experiences. Structured Knowledge

Representation System in Neocortex hippocampus Instance-Based Representation in the

Hippocampal System pattern separation: DG is crucial in selecting a distinct neural activity pattern in CA3 for each experience pattern completion : in CA3 reactivation of part of the pattern that was

activated during storage can reactivate the rest of the pattern Open question What constitutes an individual experience?

= when does hippocampus do its dance? Every moment something changes .. New experience whenever a big change in high level semantic features

Replay of Hippocampal Memories Replay of Hippocampal Memories

Circumventing the Statistics of the Environment All the experiences dont have the same priority! 1. Experience can have different lengths 2. replay is biased towards rewarding events

Novel, significant reweighting experiences shapes neocortical learning For the cortex it is the same

One shot learning? Can we apply it in AI??

DeepMind: experience replay

interleaved with ongoing game-play

biasing replay towards significant events

Prioritized experience replay

Its success supports the role of the hippocampus in reweighting experiences

external memory differentiable neural computer

Taxonomy of long-term memory ENCODING

RETRIEVAL CONSOLIDATION

ENCODING But what are these stored features? What gets actually stored?

One image, hundred ways to encode it How you encode it determines how you remember

ENCODING CONSOLIDATION

RETRIEVAL For remembering, try to

go mentally back to the situation where you learned it

Encoding what? What you encode determines what you remember! What you encode depends on your mood, attention, other thoughts and associations it is highly variable

Adult humans mostly do not encode sensory features, but rather semantic concepts Transfer learning is hard with sensory features, but easy with semantic concepts

Transfer learning Transfer learning is as good as your features Transfer learning is hard with sensory features, but

easy with semantic features As two similar things might be very different in sensory space Whereas semantic features are multisensory /

amodal different sensory features can be combined Summary

ANNs learn structured knowledge Learning single experiences is essential Based on hippocampus Prioritized replay to cortex

Applying in AI has been a success (DeepMind) One image, hundred ways to encode it Semantic encoding enables transfer

Recently Viewed Presentations

  • The Book of the Twelve - Williamsburg Baptist Church

    The Book of the Twelve - Williamsburg Baptist Church

    Hosea's Message When Israel was a child, I loved him, and out of Egypt I called my son. 2 The more I called them, the more they went from me; they kept sacrificing to the Baals, and offering incense to...
  • Unidad 9: Clases De Oraciones Simples

    Unidad 9: Clases De Oraciones Simples

    UNIDAD 9: CLASES DE ORACIONES SIMPLES 1º de Bachillerato Carmen Andreu Gisbert IES Miguel Catalán (Zaragoza) Curso 2011-2012 * * * * * * * * * * * * * 1.
  • LEAD - Environmental Public Health Today

    LEAD - Environmental Public Health Today

    LEAD Valya Dessaure, Ph.D. student Walden University PH 8165-1 Instructor: Dr. Shana Morrell Spring Quarter, 2009
  • ELL strategies and tips for teaching Science

    ELL strategies and tips for teaching Science

    Have the students write it in their Science dictionary/pictionary. ... Students need to be able to translate common words to math symbols (14.1), natural language to algebraic expressions (14.2), and algebraic expressions to natural language (14.3). The activities in this...
  • Vasectomy (Male Sterilization) Session VII: Infection Prevention Session

    Vasectomy (Male Sterilization) Session VII: Infection Prevention Session

    Establishing and maintaining a sterile field . Aseptic techniques. ... Hand hygiene is a general term referring to any action of hand cleansing that includes: ... The term "aseptic technique" refers to the practices performed just before or during a...
  • Vector-Space (Distributional) Lexical Semantics

    Vector-Space (Distributional) Lexical Semantics

    Vector-Space (Distributional)Lexical Semantics. Represent word meanings as points (vectors) in a (high-dimensional) Euclidian space. Dimensions encode aspects of the context in which the word appears (e.g. how often it co-occurs with another specific word).
  • Independent Living Program Regional Coordinators

    Independent Living Program Regional Coordinators

    Independent Living Program - Regional Coordinators Northern Bluegrass Vacant (859) 292-6340 ... Butler, Davies, Edmonson, Hancock, Henderson, Logan, McLean, Ohio, Union, Webster Eastern Mountain Brittney Blankenship (606)788-7100
  • Database Models: Flat Files and the Relational Database

    Database Models: Flat Files and the Relational Database

    Database Models: Flat Files and the Relational Database Objectives: Understand the fundamental structure of the relational database model Learn the circumstances under which it is a better choice than the flat file What is a database? Structured Data Procedures for...