debasishg

1. Feature Learning

• Learning Feature Representations with K-means by Adam Coates and Andrew Y. Ng
• The devil is in the details: an evaluation of recent feature encoding methods by Chatfield et. al.
• Emergence of Object-Selective Features in Unsupervised Feature Learning by Coates, Ng
• Scaling Learning Algorithms towards AI Benjio & LeCun
• A Theory of Feature Learning by Brendan van Rooyen, Robert C. Williamson

2. Deep Learning

• Dropout: A Simple Way to Prevent Neural Networks from Overfitting by Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever and Ruslan Salakhutdinov
• [Understanding

nmayorov

marc-hanheide

A didactic HMM implementation in Python

This code is a simple implementation of an HMM including Baum-Welche Training, Forward-Backward Algorithm, and Viterbi decoding for short and discrete obervation sequences. The example implemented here is for a robot to localise when in a lift, stoppping at three floors STATES=['F1, 'F2', 'F3'] and observing a light on each floor OBS = ['L1', 'L2', 'L3'], but that observation is being noisy, i.e. the robot might see the wrong light.

An example pre-defined HMM looks like this:

def example_hmm():
    hmm = {

aiworld

name: "GTANet"

# Can be used with pretrained Caffenet (AlexNet architecture).
# Layers with names containing 'gtanet' are not transferred from Caffenet.

layer {
  name: "gta_frames_input_layer"
  type: "HDF5Data"
  top: "images"
  top: "targets"