Novelty detection in text corpora
Pythia is Lab41's exploration of approaches to novel content detection. We are interested in making it easier to tell when a document coming into a corpus has something ne
torchnet is a framework for torch which provides a set of abstractions aiming at encouraging code re-use as well as encouraging modular programming.
At the moment, torchnet provides four set of important classes:
PyConvNet: CNN for Python
PyConvNet is a python implementation of convolutional neural network.
To train LeNet on MNIST dataset, just do as follow(you may need some python package such as numpy matplotlib):
Caffe to TensorFlow
Convert Caffe models to TensorFlow.
Run convert.py to convert an existing Caffe model to TensorFlow.
Make sure you're using the latest Caffe format (see the notes section for more info).
Unsupervised Learning on Neural Network Outputs
This repo contains the experiment code in paper
Unsupervised Learning on Neural Network Outputs: with Application in Zero-shot Learning Yao Lu International Joint Conference on Art
IPython notebook for training multilayer LSTM and RNN networks with pycaffe
Example of generated code after training on the Linux kernel for a few hours (average test loss ~1):
static int __init bit_next_wor
SpeechBot is a Telegram bot written in Python that converts anything you say into a voice message using Google's Text-to-Speech API.