Psychology 209 – Winter 2017 March 9, 2017

Slides:



Advertisements
Similar presentations
Pat Langley School of Computing and Informatics Arizona State University Tempe, Arizona USA Modeling Social Cognition in a Unified Cognitive Architecture.
Advertisements

Cognitive Systems, ICANN panel, Q1 What is machine intelligence, as beyond pattern matching, classification and prediction. What is machine intelligence,
Evolutionary Neural Logic Networks for Breast Cancer Diagnosis A.Tsakonas 1, G. Dounias 2, E.Panourgias 3, G.Panagi 4 1 Aristotle University of Thessaloniki,
An Introduction to Artificial Intelligence Presented by : M. Eftekhari.
1 Lecture 35 Brief Introduction to Main AI Areas (cont’d) Overview  Lecture Objective: Present the General Ideas on the AI Branches Below  Introduction.
Modeling and Validation Victor R. Basili University of Maryland 27 September 1999.
Genetic Algorithms Learning Machines for knowledge discovery.
Polyscheme John Laird February 21, Major Observations Polyscheme is a FRAMEWORK not an architecture – Explicitly does not commit to specific primitives.
Cognitive level of Analysis
Mathematics the Preschool Way
The impact of peer- assisted sentence- combining teaching on primary pupils’ writing.
SWARM INTELLIGENCE IN DATA MINING Written by Crina Grosan, Ajith Abraham & Monica Chis Presented by Megan Rose Bryant.
1 Using R for consumer psychological research Research Analytics | Strategy & Insight September 2014.
The Thinking Machine Based on Tape. Computer Has Some Intelligence Now Playing chess Solving calculus problems Other examples:
Knowledge and Memory: How we conceptualize information.
Introduction GAM 376 Robin Burke Winter Outline Introductions Syllabus.
Overview of Cognitive Science for Teachers
CS212: DATA STRUCTURES Lecture 1: Introduction. What is this course is about ?  Data structures : conceptual and concrete ways to organize data for efficient.
Social Cognition Psych. 414 Prof. Jessica Sommerville.
2009 ML Project: Goal: Do some real machine learning… A project you are interested in works better Data is often the hard part (get it in plenty of time)
Anomalous monism Michael Lacewing uk.
Dendral: A Case Study Lecture 25.
Copyright © 2014 McGraw-Hill Education. All rights reserved. No reproduction or distribution without the prior written consent of McGraw-Hill Education.
Level 1 Tell List Describe Locate Write State Name What happened after? How many? Who was it that...? Describe what happened at...? Who spoke to...? Can.
RULES Patty Nordstrom Hien Nguyen. "Cognitive Skills are Realized by Production Rules"
Artificial Intelligence: Research and Collaborative Possibilities a presentation by: Dr. Ernest L. McDuffie, Assistant Professor Department of Computer.
Y Letson 2007 (Miell et al 2002) Social Constructivist Approach to Learning.
CSC-305 Design and Analysis of AlgorithmsBS(CS) -6 Fall-2014CSC-305 Design and Analysis of AlgorithmsBS(CS) -6 Fall-2014 Design and Analysis of Algorithms.
Software Defects Cmpe 550 Fall 2005
Creativity of Algorithms & Simple JavaScript Commands
Measuring Growth Mindset in the Classroom
Shared Intentionality
Assessment.
Ryle’s philosophical behaviourism
What is cognitive psychology?
Neural Network Architecture Session 2
Interactive Topic Test
Analysis of Computing Options at ISU
Assessment.
CHAPTER 1 Introduction BIC 3337 EXPERT SYSTEM.
Boosted Augmented Naive Bayes. Efficient discriminative learning of
Goodfellow: Chap 1 Introduction
The “revisiting” strategy in physics tutorials Joshua S
The compilation process
A I (Artificial Intelligence)
Research & Writing in CJ
Spring Courses CSCI 5922 – Probabilistic Models (Mozer) CSCI Mind Reading Machines (Sidney D’Mello) CSCI 7000 – Human Centered Machine Learning.
Reinforcement learning (Chapter 21)
Epileptic Seizure Prediction
Videos NYT Video: DeepMind's alphaGo: Match 4 Summary: see 11 min.
Intelligent Information System Lab
Market Research Firms need market research to determine whether a product is likely to be successful before they launch it and also the potential current.
//Global Warming//.
Artificial Intelligence in Healthcare
Teaching with Instructional Software
Goodfellow: Chap 1 Introduction
Exponential Functions
Starter Imagine - you did not do as well as you wanted to in a biology test, but your teacher praises you for working hard and trying your best. You feel.
Psychology 209 – Winter 2018 March 8, 2018
Metaheuristic methods and their applications. Optimization Problems Strategies for Solving NP-hard Optimization Problems What is a Metaheuristic Method?
UMBC CMSC 104 – Section 01, Fall 2016
3.1.1 Introduction to Machine Learning
Cognition (Thinking) Refers to all mental activities associated with thinking, knowing, remembering, & communication.
Symbolic AI 2.0 Yi Zhou.
Psychology of Thinking: Embedding Artifice in Nature
Manage testing by time boxes
Toward a Great Class Project: Discussion of Stoianov & Zorzi’s Numerosity Model Psych 209 – 2019 Feb 14, 2019.
Psychology 209 – Winter 2019 March 7, 2019
This presentation was developed by Dr. Steven C
Morteza Kheirkhah University College London
Presentation transcript:

Psychology 209 – Winter 2017 March 9, 2017 Successes, Limitations, and Future Directions for Neural Network Models of Cognition Psychology 209 – Winter 2017 March 9, 2017

What cool things can neural networks learn to do? Classify pictures of objects Translate from one language to another, even without direct experience on the particular language pair Learn a strategy for searching through a random graph

What are they still struggling to do?

Lake et al Pattern recognition vs model building: Cognition is about using these models to understand the world, to explain what we see, to imagine what could have happened that didn’t, or what could be true that isn’t, and then planning actions to make it so.

Start up software Intuitive physics Intuitive psychology Infants have primitive object concepts that allow them to track objects over time and allow them to discount physically implausible trajectories – e.g. they know that objects will persist over time and that they are solid and coherent. Intuitive psychology Infants understand that other people have mental states like goals and beliefs, and this understanding strongly constrains their learning and predictions.

Learning as model building Explaining observed data through the construction of causal models of the world. ‘Early present capacities for intuitive physics and psychology are also causal models of the world’. A primary job of learning is to extend and enrich these models and build analogous causally-structured theories of other domains. Human learning is richer and more efficient than state-of-the-art algorithms in machine learning Compositionality and learning to learn are ingredients that make this type of rapid model learning possible

Model Based and Model Free Methods Using a model is cumbersome and slow; model free reinforcement learning can allow real-time ‘control’. Humans combine MB and MF competitively and cooperatively

Two Challenges Characters Frostbite

One example supports Classification of new examples Generation of new examples Parsing an object into its parts Generation of new concepts from related examples

Lake et al’s solution

How might you address this challenge using neural networks?

DQN learns Frostbyte slowly – people can do well from brief instruction or from watching a good player Construct an igloo Jump on white ice flows Gather fish Don’t fall in the water Avoid geese & polar bears

How might you address this challenge using neural networks?

Emergent intelligence vs built-in intelligence May be easier to create Since it is designed, it is likely to be easier to understand You need to have just the right stuff to get the stuff you want to learn to fit within it May not deal with quasiregularity Emergent Not as easy to create Not as easy to understand Deals with quairegularity Involves less prior commitment to structure

What other challenges can you envision?