nnlr

Learning rate controller

Adds layer-wise learning rate schemes to a deep neural network implementation

Add layer-wise learning rate schemes to Torch

GitHub

47 stars
6 watching
6 forks
Language: Lua
last commit: over 7 years ago
Linked from 1 awesome list


Backlinks from these awesome lists:

Related projects:

Repository Description Stars
rlowrance/kernel-smoothers Implementations of smoothing techniques from statistical learning theory in Lua for use with the Torch 3 deep learning framework. 5
torch/nngraph Graphical computation library for building neural network architectures 299
kaixhin/nninit Provides parameter initialisation schemes for neural network modules in Torch7 100
torch/demos Torch7 tutorials and demos providing hands-on experience with the deep learning framework. 355
nicholas-leonard/dp A deep learning library for streamlining research and development using the Torch7 distribution. 343
hleuwer/luasnmp A Lua binding to the net-snmp library for monitoring network devices 11
glouw/tinn A lightweight neural network library for training and prediction tasks 2,108
microsoft/archai Automates the search for optimal neural network configurations in deep learning applications 467
ghollisjr/cl-ana A modular Common Lisp framework for data analysis and visualization 197
rwenqi/nbd-glra A MATLAB implementation of a deep learning-based deconvolution algorithm using generalized low-rank approximation for image restoration. 21
codeplea/genann A minimal C library for training and using feedforward artificial neural networks 2,010
pathak22/context-encoder Unsupervised feature learning by image inpainting using Generative Adversarial Networks (GANs) 885
ne7ermore/torch-light A comprehensive PyTorch-based deep learning repository with examples and implementations of various models and techniques. 535
nashory/gans-collection.torch A collection of Torch implementations for training various types of Generative Adversarial Networks (GANs) 55
devendrachaplot/deeprl-grounding Trains an RL agent to execute natural language instructions in a 3D environment using a combination of A3C and gated attention mechanisms. 237