Top Banner
Babies and Computers Are They Related? – Abel Nyamapfene
26

Babies and computers - Are they related?

Dec 17, 2014

Download

Education

Abel Nyamapfene

Talk presented to undergraduate Computer Science students at the University of Exeter (Feb 2009)
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Page 1: Babies and computers - Are they related?

Babies and Computers

Are They Related? – Abel Nyamapfene

Page 2: Babies and computers - Are they related?

Abstract:

Current opinion suggests that language is a cognitive process in

which different modalities such as perceptual entities,

communicative intentions and speech are inextricably linked. In

this talk I discuss my belief that the problems psychologists are

grappling with in child development are also the same problems

computer scientists working in artificial intelligence and robotics

are facing. I show how computational modelling, in conjunction

with the availability of empirical data, has contributed to our

understanding of child language acquisition, and how this

knowledge has advanced progress in robotics.

Page 3: Babies and computers - Are they related?

Psychologist How do babies learn life skills?

How can you be as adaptive as a

baby?Computer Scientist

Page 4: Babies and computers - Are they related?

Basic Computer Organisation Von Neumann Architecture

• stored program: data and programs are stored together

• sequential control: programs that are executed sequentially.

• Algorithmic: Everything to be done defined beforehand

• Program implements algorithm in computer friendly language

Page 5: Babies and computers - Are they related?

Von Neumann Architecture Pros & Cons

Good for procedures that can be pre-defined before execution: e.g:• numerical

computation• Word processing • Car assembly• Precision surgery

Poor for procedures that

have to bee adapted on a

situation by situation

basis e.g:• Language processing• Pattern processing• Artificial human

assistant

Page 6: Babies and computers - Are they related?

Emerging Computer Applications

• Social Interaction – caregivers – domestic – helpmates

• Intelligent weaponry

• Games

• Medicine

• Education

Page 7: Babies and computers - Are they related?

Examples

humanoidsGames

Medical DiagnosticsWeapons of War

Education

Page 8: Babies and computers - Are they related?

Features Common To Intelligent Computer Applications

• Computer applications still fall far short of expectations

• Applications only work well within well specified environments

• Application scalability is limited

• Processing capability has little or no incremental capability

Page 9: Babies and computers - Are they related?

In Comparison:

Children come into the world with little or no cognitive

skills but exhibit developmental progression of increasing

processing power and complexity. An example is

language where children progress from no language, to

babbling, to one-word utterances, two-word utterances

and finally full adult speech – almost all the children .

What can Computing learn from Children?

Page 10: Babies and computers - Are they related?

Learning from Child Development

1: Carry out Empirical Investigations of Developmental Activities

- Behavioural Investigation

- Neuroscientific Investigation

2: Use Empirical Data to develop Models of Development process

3:Assess and Incrementally Improve the Models

4:Apply knowledge to computer tasks

Page 11: Babies and computers - Are they related?

Empirical Investigation:

Behavioural

• Observe developmental activity – e.g. language acquisition– Track single child from conception to stage of

full acquisition – “Keep a Diary”– Study sizeable number of children at same

stage of development– Carry out ethically approved psychological

investigations on children etc

Page 12: Babies and computers - Are they related?

Empirical Investigation: Neuroscientific

Investigate:• Brain Maturation

Processes• Interaction of Brain

Regions• Interaction of

Individual Neurons

Page 13: Babies and computers - Are they related?

Models of Development Based on Brain Neural Processing

Actual Neurons: Complex

Page 14: Babies and computers - Are they related?

Models of Development Based on Brain Neural Processing

Artificial Neurons: Very Very Simplified

Page 15: Babies and computers - Are they related?

Some Models of One-Word Child Language

“Dada” instead of “Here comes Daddy.”

“Uh oh” instead of “I am happy.”

“More” instead of “Give me some more”

Page 16: Babies and computers - Are they related?

1: A multilayer perceptron network for mapping images to text (Plunkett et al, 1992).

Network by Plunkett et al simulates word – image association and exhibits same developmental learning as a child, but learning mechanism not biologically feasible

Image (input)

Image (output)

Label representation

Label (output)

Label (input)

Image representation

joint internal representation

Page 17: Babies and computers - Are they related?

2: Hebbian-linked Self –Organising Architecture Li, Farkas & MacWhinney (2004)

activated neuron

Unidirectional links from Perception to Speech Neuron

LayersSecond SOM

First SOM

Unidirectional links from Speech and Perception Neuron Layers

Perceptual Input

Speech Input

Network was inspired by the belief that Brain Modules are interlinked. It successfully simulates Word-Object Mapping in children

Page 18: Babies and computers - Are they related?

3: An Approach that can associate Two Input Types: - Full counterpropagation network

(Hecht-Nielsen,1987)

x input layer

x output layer

cluster layer

y input layer

y output layer

Z1

Z2

ZN

Page 19: Babies and computers - Are they related?

4: Extending the Counterpropagation Approach to Modelling Child Language

(Nyamapfene &Ahmad, 2007)

Perceptual Input Speech Input

Modal

weights

Competitive Neuron layer

Intentional Input

Model based on empirical evidence that children have intentions and that brain has multimodal neurons

Page 20: Babies and computers - Are they related?

I have described some investigations of child

language acquisition through:

• Physically observing infants acquiring language

• Studying relevant brain structures

• Building, testing and modifying brain inspired computer models of child language acquisition.

Page 21: Babies and computers - Are they related?

Current Conclusions on Child Language

Acquisition Suggest That:

• Child language has multiple inputs that need to be processed simultaneously

• Language acquisition takes place through social interaction with caregivers

• Children have desires, have emotions, set and modify goals, monitor ongoing speech acts and generate communicative intentions which lead to speech utterances

Page 22: Babies and computers - Are they related?

5: A Control-Theoretic Neural Multi-Net Model of Child Language Acquisition

(Nyamapfene, 2008)

EnvironmentDesires

Emotions

Drive

Communicative

intentionsSingle-Word

Utterance

Caregiver

response

Goals

Block diagram of a control systems approach to modelling child language

at the one-word early child language acquisition stage

Child

Page 23: Babies and computers - Are they related?

From Child Development To Computing

Cynthia Breazeal has

developed Kismet, a

robot that employs drives

and emotions to interact

with a human – based

on social interaction of

an infant and a caregiver (Breazeal and Brooks, 2004)

Page 24: Babies and computers - Are they related?

Current & Future Projects

• Developing a multimodal neural network model that learns from Child - directed Speech using cross-situational techniques

• Implementing the control-theoretic model of child language acquisition presented in this talk using neural multi-nets

• Migrating child work onto a robotic platform – (circa 2009 – 2010)

Page 25: Babies and computers - Are they related?

Finally: Yes, I Think Babies and Computers are Related

Thank You!!??!!

Page 26: Babies and computers - Are they related?

References

• C. Breazeal and R. Brooks (2004). "Robot Emotion: A Functional Perspective," In J.-M. Fellous and M. Arbib (eds.) Who Needs Emotions: The Brain Meets the Robot, MIT Press (forthcoming 2004).

• R. Hecht-Nielsen (1987). “Counterpropagation Networks,” Applied Optics 26:4979-4984.

• P. Li, I. Farkas, B. MacWhinney (2004). “Early lexical development in a self-organizing neural network,” Neural Networks 17: 1345 - 1362

• A. Nyamapfene (2008). “Computational Investigation of Early Child Language Acquisition Using Multimodal Neural Networks: A Review of Three Models,” Artificial Intelligence Review (submitted).

• A. Nyamapfene and K. Ahmad (2007). “A Multimodal Model of Child Language Acquisition at the One-Word Stage,” 20th IJCNN: International Joint Conference on Neural Networks, 12th-17th August, 2007, Orlando, Florida, USA

• K. Plunkett , C. Sinha, MF. Muller, O. Strandsby (1992). “Symbol grounding or the emergence of s symbols? Vocabulary growth in children and a connectionist net,” Connection Science 4: 293-312