Papers: https://docs.google.com/document/d/1IXF3h0RU5zz4ukmTrVKVotPQypChscNGf5k6E25HGvA/edit
Codes
-
auto-encoder network (DONE)
-
constractive auto-encoders (DONE)
-
activation functions how bias changes activation functions (DONE)
-
sparse autoencoders (DONE)
-
denoising autoencoders (DONE)
-
dropout (DONE)
-
spiking neurons (DONE)
-
PCA (DONE)
-
attention (DONE)
-
maxout networks
-
invariance meshure nips09-MeasuringInvariancesDeepNetworks.pdf
-
RNN (DONE)
-
LSTM (DONE)
-
neural turing machine (DONE)
-
word2vec (DONE)
-
batch normalization (DONE)
-
PGM (DONE)
reinforcement learning
-
value iteration (DONE)
-
policy iteration (DONE)
-
monte carlo model free prediction (DONE)
-
monte carlo model free control (DONE)
-
td model free prediction (DONE)
-
td model free control (DONE)
-
q-learning (DONE)
-
sarsa (DONE)
-
off-policy stuff (DONE)
-
value function approximator (DONE)
-
action-value function approximator (DONE)
-
REINFORCE (DONE)
-
softmax policy
-
gaussian policy
-
actor-critic algorithm
-
dyna-Q algorithm
-
exploration and exploitation