Difference between revisions of "Terms"

Latest revision as of 19:10, 28 November 2018

Artificial Intelligence Nouns

@@Home -> ArtificialIntelligenceDictionary -> terms

Common Entities

• action

  *# continuous action

• action selection strategy

  *# confidence based exploration (Thrun, 1999)
  *# directed exploration
  *# eps.-greedy selection
  *# error-based directed exploration
  *# frequency-based directed exploration
  *# optimism in the face of uncertainty
  *# recency-based directed exploration (Sutton, 1990)
  *# tabu search (Abramson and Wechsler, 2003)

• activation function

  *# hyperbolic tangent activation function
  *# linear activation function
  *# logistic function
  *# monotonic activation function
  *# normal sigmoid function
  *# periodic activation function
  *# sigmoid function
  *# symmetric sigmoid function
  *# symmetric sinus activation function
  *# threshold activation function

• agent

  *# autonomous agent

• artificial intelligence
• back-propagation drawbacks

  *# local minima problem
  *# moving target problem
  *# step-size problem

• belief nets

  *# directed belief nets
  *# sigmoid belief nets

• binary codes
• cause
• cascade correlation architecture (Fahlman and Lebiere, 1990)
• conditional random fields
• connection

  *# autoregressive connections
  *# input connections
  *# lateral connection
  *# output connections
  *# short-cut connections
  *# symmetric connections
  *# temporal connections
  *# trainable connections

• containment function
• damping
• dataset

  *# labeled data
  *# noise-free data
  *# sample
  *# sequential data
  *# test set
  *# training example
  *# training patterns
  *# training data-set
  *# unbiased example
  *# unlabeled data
  *# validation data-set

• dimensionality reduction

  *# non-linear dimensionality reduction

• discount rate
• directed model
• distributed representations
• domain-specific kernel
• dynamic programming
• eligibility traces

   *# replacing eligibility traces

• energy of joint configuration
• environment

  *# stationary environment

• epoch
• error value

  *# mean square error (MSE)

• experience value

  *# discounted future experience
  *# immediate experience value

• experience value function
• factorial distribution
• feature
• generative model
• generalization
• goal state
• gradient
• greedy strategy
• inference
• layer

  *# input layer
  *# hidden layer
  *# layer of features
  *# output layer

• learning rate
• likelihood
• local optima (for neural network)
• log likelihood
• log probability
• misclassification rate
• neural networks

  *# artificial neural network (ANN)
  *# cascading neural networks
  *# convolutional multilayer neural networks
  *# counterpropagation network
  *# deep neural networks
  *# feedforward networks
  *# fully connected neural network
  *# functional-link neural networks
  *# general regression neural network
  *# higher order networks
  *# multilayer feedforward artificial neural networks
  *# multilayer neural networks
  *# probabilistic neural network
  *# real-time recurrent learning networks
  *# recurrent backpropagation networks
  *# recurrent neural networks

• neuron

  *# bias neuron
  *# binary neurons
  *# candidate neuron
  *# hidden neuron
  *# mean-field logistic unit
  *# output neuron

• node (in the network)

  *# leaf node (in the network)
  *# unit

• noise (in the data)
• objective function
• online inference
• output

  *# actual output
  *# desired output

• over-fitting
• partial derivative
• policy

  *# deterministic policy function
  *# optimal policy
  *# optimal deterministic policy
  *# stochastic policy function

• posterior distribution

  *# aggregated posterior distribution

• precision-recall curves
• prior

  *# complementary prior

• probability
• probability density models
• profit function
• reward

  *# cumulative reward
  *# discounted future reward
  *# future reward
  *# immediate reward
  *# longterm reward
  *# short-term reward

• reward value function
• root mean squared error
• second order statistics
• selective attention approach
• sensory input
• shallow models
• slackness of the bound
• sloppy top-down specification
• softmax function
• state

  *# after-state
  *# continuous state

• state-action space
• stop function
• structure (in the data)
• training curve
• value function

  *# action-value function
  *# state-value function

• variable (for neural network)

  *# circular variables
  *# stochastic variable

• weights

  *# frozen weights
  *# initial weights
  *# lateral weight

Named Entities

• Adaline
• ARTMAP Neural Networks

  *# Fuzzy ARTMAP
  *# Gaussian ARTMAP

• Bellman Optimality Equation (Sutton and Barto, 1998)
• Bernoulli Variables
• Bidirectional Associative Memory (BAM)
• Boltzmann Machine

  *# Conditional RBM model
  *# Restricted Boltzmann Machine (RBM)
  *# Semi-restricted Boltzmann Machines
  *# Temporal RBM

• Boltzmann-Gibbs Selection
• Deep Belief Nets

  *# Deep Autoencoders

• Dynamic Bayes Nets
• Elman Neural Networks
• Finite Impulse Response (FIR) filter
• Gaussian Processes
• Gaussian Unit
• Hebbian Theory
• Hidden Markov Models (HMM)
• Hopfield Net
• Jordan Neural Network
• Long Short-Term Memory (LSTM) Recurrent Network
• Markov Decision Process (MDP)
• Markov Environment
• Markov Property
• Markov State
• Max-Boltzmann Selection
• MNIST Test Set
• MRF

  *# MRF-MBNN

• Neocognitron
• Perceptron
• RBF Networks
• Support Vector Machine (SVM)
• T-step policy
• T-step return
• TF-IFD
• Threshold Logical Units (TLU) Network
• Time Delay Neural Network (TDNN)
• UNI-SNE method