emotions

1
emotions

• cse 574 winter 2004

2
emotions

• cse 574 winter 2004

3
affective computing

• R.W. Picard, Affective Computing
• limbic / cortical tangle
• lack of emotion inefficient decision making
  (theorem prover run wild?) (Damasio)
• human/human conventions hold for human/computer
  interaction (Nass)
• affective pattern recognition
• limbic system inspiration for backpropagation

• applications
• teaching
• environments
• communication tools
• entertainment
• bad faith?

4
Recognizing Emotions

• M. Dailey, G. Cottrell, R. Adlophs, A six-unit
  network is all you need to discover happiness
• Input 29x36 grid of wavelets transformation
  of image to a sum of period signals (frequency
  domain)
• Principle component analysis to reduce
  dimensionality
• Classification by 6-unit neural network
• Biologically plausible

5
(No Transcript)
6
(No Transcript)
7
(No Transcript)
8
Purposeful Emotions

• J.D. Valaqsquez, When robots weep emotional
  memories decision-making, AAAI 1998.
• Emotions as non-conscious biasing mechanism
  somatic marker of past experience functions
  as alarm or incentive (A. Damasio, Descartes
  Error)
• drives impels agent into action
• emotion system
• anger, fear, distress, happiness, disgust,
  surprise mixes
• triggered by releasers
• can learn associations between stimuli emotion
  (e.g. image of pea soup disgust)
• behavior system set of self-interested
  behaviors (play, approach)
• triggered/inhibited by drives, emotions, each
  other

9
coco
10
kismet
11
(No Transcript)
12
Big Picture

• What are the components of computational theory
  of human intelligence? What kinds of
  applications need to consider each?
• Which are universal to any kind of intelligent
  organism or artifact? Which are unique to social
  beings? To human beings?
• What are appropriate ways to model these
  phenomena? Are the models psychologically
  plausible descriptions of
• How we think?
• How we think about others?

• part 1 discourse understanding
• speech act theory
• beliefs about beliefs and goal
• planning utterances
• interpreting utterances
• the structure of discourse
• reinforcement learning in discourse analysis
• part 2 behavior recognition
• technical foundations from Markov models to
  Dynamic Bayes Nets
• modeling events with structure and continuous
  time
• learning user models
• modeling user errors and emotions
• applications
• part 3 creativity emotion
• theories of creativity
• computers that create art and music
• emotional computers