volkancirik

"""
TreeLSTM[1] implementation in Pytorch

Based on dynet benchmarks : 
  https://github.com/neulab/dynet-benchmark/blob/master/dynet-py/treenn.py
  https://github.com/neulab/dynet-benchmark/blob/master/chainer/treenn.py
Other References:
  https://github.com/pytorch/examples/tree/master/word_language_model
  https://github.com/pfnet/chainer/blob/29c67fe1f2140fa8637201505b4c5e8556fad809/chainer/functions/activation/slstm.py
  https://github.com/stanfordnlp/treelstm

karpathy

""" Trains an agent with (stochastic) Policy Gradients on Pong. Uses OpenAI Gym. """
import numpy as np
import cPickle as pickle
import gym

# hyperparameters
H = 200 # number of hidden layer neurons
batch_size = 10 # every how many episodes to do a param update?
learning_rate = 1e-4
gamma = 0.99 # discount factor for reward

kingjr

# Author: Jean-Remi King <[email protected]>
"""
    Illustrate how a hinge loss and a log loss functions 
    typically used in SVM and Logistic Regression 
    respectively focus on a variable number of samples.
    For simplification purposes, we won't consider the
    regularization or penalty (C) factors.
"""
import numpy as np
import matplotlib.animation as animation

tzutalin

name: "nin_imagenet"
input: "data"
input_shape {
  dim: 10
  dim: 3
  dim: 224
  dim: 224
}
layers {
  bottom: "data"