Jürgen Schmidhuber has written a fair amount of cool stuff.

He has a tendency to use many acronyms in his papers. This post is an attempt to summarize some of them.

Papers:

• On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models
• Deep Learning in Neural Networks: An Overview
• Evolving Large-Scale Neural Networks for Vision-Based Reinforcement Learning

General

• AI Artificial Intelligence
• AGI Artificial General Intelligence
• DL Deep Learning
• RL Reinforcement Learning
• SL Supervised Learning
• UL Unsupervised Learning

Networks

• NN Neural Network
• ANN Artificial Neural Network
• BNN Biological Neural Network
• CNN Convolutional Neural Network
• FNN Feedforward Neural Network
• RNN Recurrent Neural Network
• BRNN Bi-directional Recurrent Neural Network
• LSTM Long Short Term Memory
• BP Backpropagation
• BPTT BackPropagation Through Time

Other

• AE AutoEncoder
• AIT Algorithmic information theory
• BM Boltzmann Machine
• CAP Credit Assignment Path
• CEC Constant Error Carousel
• CFL Context Free Language
• CM Controller-Model system
• CMA-ES Covariance Matrix Estimation Evolution Strategies
• CoSyNE Co-Synaptic Neuro-Evolution
• CSL Context Senistive Language
• CTC Connectionist Temporal Classification (gradient-based method to train RNNs) paper
• DCT Discrete Cosine Transform
• DBN Deep Belief Network
• DP Dynamic Programming
• DS Direct Policy Search
• EA Evolutionary Algorithm
• EM Expectation Maximization
• FMS Flat Minimum Search
• FSA Finite State Automaton
• GMDH Group Method of Data Handling
• GOFAI Good Old-Fashioned Artificial Intelligence
• GP Genetic Programming
• GPU Graphics Processing Unit
• GP MPCNN: GPU-Based Max-Pooling Convolutional Neural Network
• HMM Hidden Markov Model
• HRL Hierarchical Reinforcement Learning
• HTM Hierarchical Temporal Memory
• HMAX Hierarchical Model “and X”
• HRL NN-based Hierarchical RL
• MC Multi-Column
• MCTS Monte Carlo Tree Sampling (also Monte Carlo Tree Search)
• MDL Minimum Description Length
• MDP Markov Decision Process
• MNIST Mixed National Institute of Standards and Technology Database
• MP Max-Pooling
• MPCNN Max-Pooling Convolutional Neural Network
• NEAT NeuroEvolution of Augmenting Topologies
• NE NeuroEvolution, (using evolutionary computation to train artifi-cial neural networks) paper
• NES Natural Evolution Strategies
• NFQ Neural Fitted Q-Learning paper
• PCC Potential Causal Connection
• PDCC Potential Direct Causal Connection
• PG Policy Gradient
• PM Predictability Minimization
• POMDP Partially Observable Markov Decision Process
• RAAM Recursive Auto-Associative Memory
• RBM Restricted Boltzmann Machine
• ReLU Rectified Linear Unit
• R-prop: Resilient Backpropagation
• RNNAI RNN-based AI
• SLIM NN: Self-Delimiting Neural Network
• SOTA Self-Organising Tree Algorithm
• SVM Support Vector Machine
• TDNN Time-Delay Neural Network
• TIMIT TI/SRI/MIT Acoustic-Phonetic Continuous Speech Corpus
• WTA Winner-Take-All
• TORCS The Open Racing Car Simulator wiki