Personality and Emotion for AI
Created @May 18, 2023 11:59 AM
Class BCSAI2023
Type Final Exam Revision
Materials
Reviewed
Professor José Ángel Martinez Huertas
Computational Processing
EPAM (Elementary Perceiver and memoriser)
Modelling N400
Emotion
Affective Computing
Charles Darwin
Paul Ekman - Facial Expressions
James A. Russel - context, age, arousal and valance
Dellaert, Polzin, & Waibel
Patel, Patel, & Mankad
Caridakis et al. (2006)
Xu et al. (2022)
Zago et al. (2022)
Martínez-Huertas, Jorge-Botana, Luzón, & Olmos (2021)
Martínez-Huertas, Jorge-Botana, & Olmos (2021)
Bibi et al. (2022)
Epigenetics
Personality
Big Five model
HEXACO model
Eysenck’s Personality Theory
Light vs. Dark Triad Personality Traits
Type A vs. Type B
AIBO Personality recognition
TensorFlow-based automatic personality recognition
Personality and Emotion for AI 1
, Personality Recognition in Spanish Texts
A meta-analytic study on computational methods
Evolution and revolution
Computational Processing
EPAM (Elementary Perceiver and memoriser)
Feigenbaum & Simon (1961, 1963)
Simulates human verbal learning through 4 principal functions:
Recognise an external stimulus
as one about which some information has already been memorised
Add new stimulus items to the memory
by building tests that allow the new item to be distinguished from stimuli previously
learned
Internally associate two stored items
say x and y, by storing with x some cue information about y
Respond to an external stimulus
respond to X with response Y, by retrieving the cue to the response, and then
retrieving the response using the cue
Discrimination net construct - central "memory structure”
A tree-like nexus for association learning process
terminal nodes of IMAGES of encodings of external stimuli, retrieved by sorting the
stimulus down through the tests of the net to find the response cue and then sorting
that cue in the same net to find the response image.
TESTS that examine bits of the encodings as non-terminal nodes
Personality and Emotion for AI 2
, Modelling N400
Rabovsky et al. 2018. Modelling the N400 brain potential as change
in a probabilistic representation of meaning.
The brain constructs a probabilistic representation of word meaning based on prior
experience, and when encountering unexpected or incongruent words, it updates this
representation, leading to the observed N400 response.
This model explains the N400 amplitudes as the change induced by an incoming word
in an implicit probabilistic representation of meaning
→ Hidden unit activation pattern in a neural network model
→ Driving implicit learning in the network
I take coffee with cream and...’ ‘dog’ (larger N400) vs. ‘sugar’
(smaller N400)
This computational model connects human language comprehension with recent
deep learning approaches to language processing by manipulating variables
which affect the N400 and explore how they affect processing.
Personality and Emotion for AI 3
Created @May 18, 2023 11:59 AM
Class BCSAI2023
Type Final Exam Revision
Materials
Reviewed
Professor José Ángel Martinez Huertas
Computational Processing
EPAM (Elementary Perceiver and memoriser)
Modelling N400
Emotion
Affective Computing
Charles Darwin
Paul Ekman - Facial Expressions
James A. Russel - context, age, arousal and valance
Dellaert, Polzin, & Waibel
Patel, Patel, & Mankad
Caridakis et al. (2006)
Xu et al. (2022)
Zago et al. (2022)
Martínez-Huertas, Jorge-Botana, Luzón, & Olmos (2021)
Martínez-Huertas, Jorge-Botana, & Olmos (2021)
Bibi et al. (2022)
Epigenetics
Personality
Big Five model
HEXACO model
Eysenck’s Personality Theory
Light vs. Dark Triad Personality Traits
Type A vs. Type B
AIBO Personality recognition
TensorFlow-based automatic personality recognition
Personality and Emotion for AI 1
, Personality Recognition in Spanish Texts
A meta-analytic study on computational methods
Evolution and revolution
Computational Processing
EPAM (Elementary Perceiver and memoriser)
Feigenbaum & Simon (1961, 1963)
Simulates human verbal learning through 4 principal functions:
Recognise an external stimulus
as one about which some information has already been memorised
Add new stimulus items to the memory
by building tests that allow the new item to be distinguished from stimuli previously
learned
Internally associate two stored items
say x and y, by storing with x some cue information about y
Respond to an external stimulus
respond to X with response Y, by retrieving the cue to the response, and then
retrieving the response using the cue
Discrimination net construct - central "memory structure”
A tree-like nexus for association learning process
terminal nodes of IMAGES of encodings of external stimuli, retrieved by sorting the
stimulus down through the tests of the net to find the response cue and then sorting
that cue in the same net to find the response image.
TESTS that examine bits of the encodings as non-terminal nodes
Personality and Emotion for AI 2
, Modelling N400
Rabovsky et al. 2018. Modelling the N400 brain potential as change
in a probabilistic representation of meaning.
The brain constructs a probabilistic representation of word meaning based on prior
experience, and when encountering unexpected or incongruent words, it updates this
representation, leading to the observed N400 response.
This model explains the N400 amplitudes as the change induced by an incoming word
in an implicit probabilistic representation of meaning
→ Hidden unit activation pattern in a neural network model
→ Driving implicit learning in the network
I take coffee with cream and...’ ‘dog’ (larger N400) vs. ‘sugar’
(smaller N400)
This computational model connects human language comprehension with recent
deep learning approaches to language processing by manipulating variables
which affect the N400 and explore how they affect processing.
Personality and Emotion for AI 3
