Upload File

learning

26
Learning Any relatively permanent change in behavior (or behavior potential) produced by experience

Upload: nicholas-schneider

Post on 30-Dec-2015

10 views

Category:

Documents


0 download

Report

Tags:

DESCRIPTION

Learning. Any relatively permanent change in behavior (or behavior potential) produced by experience. Association. We learn by association Our minds naturally connect events that occur in sequence Aristotle 2000 years ago John Locke and David Hume 200 years ago Associative Learning - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: Learning

Learning

Any relatively permanent change in behavior (or behavior potential) produced by experience

Page 2: Learning

Association

We learn by association Our minds naturally connect events that

occur in sequence Aristotle 2000 years ago John Locke and David Hume 200 years ago

Associative Learning learning that two events occur together

two stimuli a response and its consequences

Page 3: Learning

Classical or Pavlovian Conditioning

We learn to associate two stimuli

Page 4: Learning

Classical Conditioning

Ivan Pavlov studies digestion in dogs (1904) Conditions dogs to salivate to a sound (bell

or buzzer) Determines formula for the conditioning

process UCS = UCR NS + UCS = UCR CS = CR

Best case: NS precedes UCS Worst case: NS follows UCS

Page 5: Learning

Classical ConditioningUCS(passionate kiss) UCR

(sexualarousal)

CS(onionbreath)

CS(onion breath) CR

(sexualarousal)

UCS(passionate Kiss) UCR

(sexualarousal)

Page 6: Learning

Characteristics of Conditioning Generalization: the tendency of stimuli

similar to the original conditioned stimulus to evoke a similar conditioned response

Discrimination: to be able to differentiate between stimuli

Extinction: a process by which the effects of conditioning are reduced and finally disappear

Spontaneous recovery: the reappearance of a learned response after its apparent extinction

Page 7: Learning

Characteristics of Conditioning (cont.)

Higher-order conditioning: a neutral stimulus becomes a conditioned stimulus through association with an already established conditioned stimulus

Page 8: Learning

Operant Conditioning

We learn to associate a response and its consequence

Page 9: Learning

Operant Conditioning

Definition: behavior is shaped by the consequences it produces

We “learn” by doing things that produce positive outcomes and/or allow us to avoid negative outcomes (sometimes negative is better than none at all)

Page 10: Learning

Operant Conditioning

Reinforcer any event that strengthens the

behavior it follows Shaping

operant conditioning procedure in which reinforcers guide behavior toward closer approximations of a desired goal

Page 11: Learning

Operant Conditioning (cont.)

Primary reinforcers: they satisfy a biological need – food, water, sex (we need to feel a deficit of it for it to be a reinforcer)

Secondary reinforcers: they take on the ability to reinforce – e.g. money, status, praise

Positive reinforcers: the behavior is strengthened to get the reward

Negative reinforcers: the behavior is strengthened to avoid the reinforcer

Punishment: the behavior is weakened to avoid the reinforcer

Page 12: Learning

Operant Conditioning

Page 13: Learning

Punishment

Page 14: Learning

Schedules of Reinforcement

Continuous Reinforcement reinforcing the desired response each time

it occurs Partial (Intermittent) Reinforcement

reinforcing a response only part of the time results in slower acquisition greater resistance to extinction

Page 15: Learning

Schedules of Reinforcement

Fixed Ratio (FR) Schedule reinforces a response only after a

specified number of responses faster you respond the more rewards

you get different ratios very high rate of responding like piecework pay

Page 16: Learning

Schedules of Reinforcement

Variable Ratio (VR) reinforces a response after an

unpredictable number of responses

average ratios like gambling, fishing very hard to extinguish because

of unpredictability

Page 17: Learning

Schedules of Reinforcement

Fixed Interval (FI) reinforces a response only after

a specified time has elapsed response occurs more

frequently as the anticipated time for reward draws near

Page 18: Learning

Schedules of Reinforcement

Variable Interval (VI) reinforces a response at

unpredictable time intervals produces slow steady responding like pop quiz

Page 19: Learning

Schedules of Reinforcement

Variable Interval

Number of responses

1000

750

500

250

010 20 30 40 50 60 70

Time (minutes)

Fixed Ratio

Variable Ratio

Fixed Interval

Steady responding

Rapid respondingnear time forreinforcement

80

Page 20: Learning

Operant vs Classical Conditioning

Page 21: Learning

Cognition and Operant Conditioning

Cognitive Map mental representation of the layout of

one’s environment Example: after exploring a maze, rats act

as if they have learned a cognitive map of it

Latent Learning learning that occurs, but is not apparent

until there is an incentive to demonstrate it

Page 22: Learning

Cognition and Operant Conditioning

Intrinsic Motivation desire to perform a behavior for

its own sake and to be effective Extrinsic Motivation

desire to perform a behavior due to promised rewards or threats of punishments

Page 23: Learning

Observational Learning

Observational Learning learning by observing others

Modeling process of observing and imitating a specific behavior

Page 24: Learning

Observational Learning

Alfred Bandura’s Experiments Bobo doll we look and we learn

Page 25: Learning

Observational Learning

Prosocial Behavior positive, constructive, helpful behavior

opposite of antisocial behavior

Page 26: Learning

Television and Observational Learning


LEARNING OUTCOMES Teaching, learning and assessment methods Learning Outcomes TLA 2.… · LEARNING OUTCOMES Teaching, learning and assessment ... number of teaching/learning and

Deep Learning for Reinforcement Learning in · PDF fileDeep Learning for Reinforcement Learning in ... Deep Learning for Reinforcement Learning in Pacman Deep Learning für ... Während

Optimising Learning: Implications of Learning Sciences ...Learning sciences is an interdisciplinary field that studies teaching and learning. Learning scientists study learning in

Assessment for Learning - Curriculum · Assessment for Learning Assessment for Learning Assessment of Learning ... Sharing Learning Intentions 1. Identify what pupils will be learning

Suggested Machine Learning Class: – learning-supervised-learning--ud675

LEARNING Chapter: Learning

Learning organizations, ideal organizations, learning, Single loop learning, Double – loop learning, Organizational Learning, Traditional organization,

A learning outcomes approach approach Learning... ·  · 2008-12-21- learning outcomes approach ... Learning Outcomes All learning at whatever level can be ... Write learning outcomes

Professional Learning in the Learning Profession - Learning Forward

machine Learning Learning

Learning, E-Learning & Re-Learning: Leadership … @diversitywoman The Innovation of Human Capital: Inclusion & Learning Learning, E-Learning & Re-Learning: Leadership Success in the

 · The learning where learner uses multimedia learning environments. This type of learning relies on dual-coding theory. 3.3.1 e-Learning and m-Learning Electronic learning or e-learning

2012 - TD PHL · © Bobbe G Baggio 2012 What exactly is e-Learning any? Elearning E-learning elearning e-Learning e-learning Online learning Web-based learning Distance learning

Eick: Reinforcement Learning. Reinforcement Learning Introduction Passive Reinforcement Learning Temporal Difference Learning Active Reinforcement Learning

Learning Environments - Informing Scienceproceedings.informingscience.org/InSITE2010/InSITE... · Key Words: M-Learning, Collaborative Learning, Natural Learning, Learning Environments

Learning and Knowledge Microlearning 2006. Business is learning Life is learning Education is learning Aging is learning What isnt learning???

LEARNING ABOUT LEARNING Learning Communities in Higher Education

Grundtvig Learning Partnership 2011-2013 LIFELONG LEARNING PROGRAMME GRUNDTVIG LEARNING PARTNERSHIP LEARNING PARENTS

Widely Acclaimed but Lowly Utilized: Congruencing ODL ... · distance education, electronic learning (e-Learning), mobile learning (m-Learning) or blended learning (b-Learning). ODL

Learning What is learning? Classical Conditioning Operant Conditioning Applications of learning Cognitive Learning

Learning Deep Learning

Understanding Learning Styles Differences in the Learning ... · Understanding Learning Styles Differences in the Learning and Work Environment Your Learning Style in the Formal Learning

Statistical Learning - homepage.divms.uiowa.edu€¦ · Statistical Learning Some Machine Learning Terminology Two forms of learning: – supervised learning: features and responses

GROUP WORK. Group Work Other names: cooperative learning collaborative learning collective learning peer teaching/learning reciprocal learning team learning

LinkedIn Learning | What We're Learning About Learning

Unsupervised Learning Learning Unsupervised...Unsupervised Learning and Data Mining Learning Mining Unsupervised Learning and Data Mining Unsupervised Data Clustering Supervised Learning

Learning Objective 1 Learning Objective 2 Learning

B learning, m-learning, e-learning

By Justin Beene. Learning the string names Learning the A chord Learning the B chord Learning the C chord Learning the D chord Learning the E chord Learning

EDFD 302 MGMSANTOS Learning Models. Learning Models: Mastery Learning Discovery Learning Guided Discovery Learning Meaningful Reception Learning

Learning about Learning

Guided Learning Projects Messy Learning – Real Learning – Successful Learning

E-LEARNING , B-LEARNING Y M-LEARNING

Learning Reinforcement Learning by Learning REINFORCE

Deep Learning for Reinforcement Learning in Pacman · Deep Learning for Reinforcement Learning in Pacman Deep Learning für Reinforcement Learning in Pacman Vorgelegte Bachelor-Thesis