LibN3L: A light-weight neural network package for natural language
-
Updated
Dec 22, 2015 - C++
Deep learning is an AI function and a subset of machine learning, used for processing large amounts of complex data. Deep learning can automatically create algorithms based on data patterns.
LibN3L: A light-weight neural network package for natural language
Minerva: a fast and flexible tool for deep learning on multi-GPU. It provides ndarray programming interface, just like Numpy. Python bindings and C++ bindings are both available. The resulting code can be run on CPU or GPU. Multi-GPU support is very easy.
[ICCV 2015] Framework for optimizing CNNs with linear constraints for Semantic Segmentation
Yet another replication of ``Human-level control through deep reinforcement learning''.
Code release of "Deep Hashing Network for Efficient Similarity Retrieval" (AAAI 16)
The SimNets Architecture's Implementation in Caffe
RedEye is a vision sensor designed to execute early stages of a deep convolutional neural network (ConvNet) in the analog domain. This repo is a modification of Caffe to train, simulate and visualize analog ConvNet processing under noise vs. energy tradeoffs.
Given an input and output directory this code generates N random transformations for each image of the input directory.
Named Entity Recognition (NER) models (neural and sparse) implemented based on package LibN3L
Naive implementation of popular stochastic optimizers
Optimal Convergence Rate in Deep Neural Networks using HJB equation
Sex recognizer using CUDA and deep learning.
Simple implementation of a feedforward neural network in c++
UnitBox: An Advanced Object Detection Network
PArallel Distributed Deep LEarning
Demitasse: SPMD Programing Implementation of Deep Neural Network Library for Mobile Devices(NeurIPS2016WS)
A Clean Lua Interface to the Indri Search Engine for Torch.
Supervised Semantics-preserving Deep Hashing (TPAMI18)