Presentation is loading. Please wait.

Presentation is loading. Please wait.

The PDP Approach to Understanding the Mind and Brain J. McClelland Cognitive Core Class Lecture March 7, 2011.

Similar presentations


Presentation on theme: "The PDP Approach to Understanding the Mind and Brain J. McClelland Cognitive Core Class Lecture March 7, 2011."— Presentation transcript:

1 The PDP Approach to Understanding the Mind and Brain J. McClelland Cognitive Core Class Lecture March 7, 2011

2 Decartes’ Legacy Mechanistic approach to sensation and action Divine inspiration creates mind This leads to four dissociations: –Mind / Brain –Higher Cognitive Functions / Sensory-motor systems –Human / Animal –Descriptive / Mechanistic

3 Early Computational Models of Human Cognition (1950-1980) The computer contributes to the overthrow of behaviorism. Computer simulation models emphasize strictly sequential operations, using flow charts. Simon announces that computers can ‘think’. Symbol processing languages are introduced allowing some success at theorem proving, problem solving, etc. Minsky and Pappert kill off Perceptrons. Cognitive psychologists distinguish between algorithm and hardware. Neisser deems physiology to be only of ‘peripheral interest’ Psychologists investigate mental processes as sequences of discrete stages.

4

5 Ubiquity of the Constraint Satisfaction Problem In sentence processing –I saw the grand canyon flying to New York –I saw the sheep grazing in the field In comprehension –Margie was sitting on the front steps when she heard the familiar jingle of the “Good Humor” truck. She remembered her birthday money and ran into the house. In reaching, grasping, typing…

6

7 Graded and variable nature of neuronal responses

8 Lateral Inhibition in Eye of Limulus (Horseshoe Crab)

9 The Interactive Activation Model

10 Distributed Representations in the Brain: Overlapping Patterns for Related Concepts (Kiani et al, 2007) doggoathammer dog goat hammer Many hundreds of single neurons recorded in monkey IT. 1000 different photographs were presented twice each to each neuron. Hierarchical clustering based on the distributed representation of each picture: –The pattern of activation over all the neurons

11 Kiani et al, J Neurophysiol 97: 4296–4309, 2007.

12 The Rumelhart Model The Quillian Model

13 1.Show how learning could capture the emergence of hierarchical structure 2.Show how the model could make inferences as in the Quillian model DER’s Goals for the Model

14 ExperienceExperience Early Later Later Still

15 Start with a neutral representation on the representation units. Use backprop to adjust the representation to minimize the error.

16 The result is a representation similar to that of the average bird…

17 Use the representation to infer what this new thing can do.

18 Questions About the Rumelhart Model Does the model offer any advantages over other approaches? –Do distributed representations really buy us anything? –Can the mechanisms of learning and representation in the model tell us anything about Development? Effects of neuro-degeneration?

19 Phenomena in Development Progressive differentiation Overgeneralization of –Typical properties –Frequent names Emergent domain-specificity of representation Basic level advantage Expertise and frequency effects Conceptual reorganization

20 Disintegration in Semantic Dementia Loss of differentiation Overgeneralization

21 The Hierarchical Naïve Bayes Classifier Model (with R. Grosse and J. Glick) The world consists of things that belong to categories. Each category in turn may consist of things in several sub-categories. The features of members of each category are treated as independent –P({f i }|C j ) =  i p(f i |C j ) Knowledge of the features is acquired for the most inclusive category first. Successive layers of sub- categories emerge as evidence accumulates supporting the presence of co-occurrences violating the independence assumption. Living Things … Animals Plants Birds Fish Flowers Trees

22 PropertyOne-Class Model1 st class in two-class model 2 nd class in two-class model Can Grow1.0 0 Is Living1.0 0 Has Roots0.51.00 Has Leaves0.43750.8750 Has Branches0.250.50 Has Bark0.250.50 Has Petals0.250.50 Has Gills0.2500.5 Has Scales0.2500.5 Can Swim0.2500.5 Can Fly0.2500.5 Has Feathers0.2500.5 Has Legs0.2500.5 Has Skin0.501.0 Can See0.501.0 A One-Class and a Two-Class Naïve Bayes Classifier Model

23 Accounting for the network’s feature attributions with mixtures of classes at different levels of granularity Regression Beta Weight Epochs of Training Property attribution model: P(f i |item) =  k p(f i |c k ) + (1-  k )[(  j p(f i |c j ) + (1-  j )[…])

24 Should we replace the PDP model with the Naïve Bayes Classifier? It explains a lot of the data, and offers a succinct abstract characterization But –It only characterizes what’s learned when the data actually has hierarchical structure So it may be a useful approximate characterization in some cases, but can’t really replace the real thing.

25 Structure Extracted by a Structured Statistical Model

26

27 Predictions Similarity ratings (and patterns of inference) will violate the hierarchical structure Patterns of inference will vary by context

28 Experiments Size, predator/prey, and other properties affect similarity across birds, fish, and mammals Property inferences show clear context specificity Future experiments will examine whether inferences (even of biological properties) violate a hierarchical tree for items like weasels, pandas, and beavers

29 The Nature of Cognition, and the Place of PDP in Cognitive Theory? Many view human cognition as inherently –Structured –Systematic –Rule-governed In this framework, PDP models are seen as –Mere implementations of higher-level, rational, or ‘computational level’ models –… that don’t work as well as models that stipulate explicit rules or structures

30 The Alternative We argue instead that cognition (and the domains to which cognition is applied) is inherently –Quasi-regular –Semi-systematic –Context sensitive On this view, highly structured models: –Are Procrustian beds into which natural cognition fits uncomfortably –Won’t capture human cognitive abilities as well as models that allow a more graded and context sensitive conception of structure

31 Levels of Analysis Marr (1982) suggested we should analyze cognitive tasks at three levels: –Computation: what are the goals, what information is available, how could the information be used to achieve the goals; what is the best that can be done with the given information? –Algorithms and representations: How is information represented? What algorithms are used in manipulating representations? –Implementation: How are the algorithms and representations implemented in neural circuitry? PDP models often closely approximate (and can in many cases exactly match) idealized competence models (including structured probabilistic models). Which is the approximation? The PDP approach encourages computational level analysis but asks many questions about it: –How do we know what task – which computations – an organism is actually trying to carry out? –Is performance constrained by tasks the organism was trying to perform when it evolved or that it has performed habitually? Such constraints may be ‘wired into’ the processing mechanism, constraining its performance and preventing optimality for a given task. –The approach leads us to ask: How does the architecture and/or type of processing machinery constrain the problem and its solution? Perhaps performance is being optimized within such constraints? The PDP approach also blurs the distinction between the algorithmic and implementation levels –PDP models generally do not concern themselves with the minute details of neural implementation, and their performance often approximates performance that would be achieved by an explicit algorithm – thus they appear to lie between Marr’s algorithmic and implementation levels –PDP models do not deny that there are temporally extended cognitive processes, e.g. in problem solving and planning, that involve many steps and that can often be usefully characterized in terms of a sequence of discrete states (but leave open the possibility that insight and creativity short-circuit such processes). –The automatic and intuition-based nature of PDP models may, however, be very relevant even in our most advanced forms of cognition.


Download ppt "The PDP Approach to Understanding the Mind and Brain J. McClelland Cognitive Core Class Lecture March 7, 2011."

Similar presentations


Ads by Google