Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
♾A curated list of papers and code about very deep neural networks
| Date | Stars |
|---|---|
| 2026-07-31 | 456 |
| 2026-08-03 | 456 |
| 2026-08-04 | 456 |
| 2026-08-06 | 456 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center"> <img width='600px' src="http://i.imgur.com/XjCXXap.png"><br><br> </div> ----------------- **awesome-very-deep-learning** is a curated list for papers and code about implementing and training very deep neural networks. ## Neural Ordinary Differential Equations **ODE Networks** are a kind of continuous-depth neural network. Instead of specifying a discrete sequence of hidden layers, they parameterize the derivative of the hidden state using a neural network. The output of the network is computed using a black-box differential equation solver. These continuous-depth models have constant memory cost, adapt their evaluation strategy to each input, and can explicitly trade numerical precision for speed. ### Papers - [Neural Ordinary Differential Equations (2018)](https://arxiv.org/abs/1806.07366) [[original code]](https://github.com/rtqichen/torchdiffeq), introduces several ODENets such as continuous-depth residual networks and continuous-time latent variable models. The paper also constructs continuous normalizing flows, a generative model that can train by maximum likelihood, without partitioning or ordering the data dimensions. For training, the authors show how to scalably backpropagate through any ODE solver, without access to its internal operations. This allows end-to-end training of ODEs within larger models. NIPS 2018 best paper. - [Augmented Neural ODEs (2019)](https://arxiv.org/abs/1904.01681), neural ODEs preserve topology, thus their learned flows can't intersect with each other. Therefore some functions can't be learned. Augmented NODEs improve upon this by adding an additional dimension to learn simpler flows. ### Implementations 1. Authors [Autograd Implementation](https://github.com/HIPS/autograd/blob/master/examples/ode_net.py) ## Value Iteration Networks **Value Iteration Networks** are very deep networks that have tied weights and perform approximate value iteration. They are used as an internal (model-based) planning module. ### Papers - [Value Iteration Networks (2016)](https://arxiv.org/abs/1602.02867) [[original code](https://github.com/avivt/VIN)], introduces VINs (Value Iteration Networks). The author shows that one can perform value iteration using iterative usage of convolutions and channel-wise pooling. It is able to generalize better in environments where a network needs to plan. NIPS 2016 best paper. ## Densely Connected Convolutional Networks **Densely Connected Convolutional Networks** are very deep neural networks consisting of dense blocks. Within dense blocks, each layer receives the feature maps of all preceding layers. This leverages feature reuse and thus substantially reduces the model size (parameters). ### Papers - [Densely Connected Convolutional Networks (2016)](https://arxiv.org/abs/1608.06993) [[original code](https://github.com/liuzhuang13/DenseNet)], introduces DenseNets and shows that it outperforms ResNets in CIFAR10 and 100 by a large margin (especially when not using data augmentation), while only requiring half the parameters. CVPR 2017 best paper. ### Implementations 1. Authors' [Caffe Implementation](https://github.com/liuzhuang13/DenseNetCaffe) 0. Authors' more memory-efficient [Torch Implementation](https://github.com/gaohuang/DenseNet_lite). 0. [Tensorflow Implementation](https://github.com/YixuanLi/densenet-tensorflow) by Yixuan Li. 0. [Tensorflow Implementation](https://github.com/LaurentMazare/deep-models/tree/master/densenet) by Laurent Mazare. 0. [Lasagne Implementation](https://github.com/Lasagne/Recipes/tree/master/papers/densenet) by Jan Schlüter. 0. [Keras Implementation](https://github.com/tdeboissiere/DeepLearningImplementations/tree/master/DenseNet) by tdeboissiere. 0. [Keras Implementation](https://github.com/robertomest/convnet-study) by Roberto de Moura Estevão Filho. 0. [Chainer Implementation](https://github.com/t-hanya/chainer-DenseNet) by Toshinori Hanya. 0. [Chainer Implementation](https://github.com/yasunorikud
Excerpt of 13,625 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:de70dcd0353f4e33, topic:awesome-list, desc:curated list, readme:curated list
matched fp:de70dcd0353f4e33, topic:deep-learning, readme:autograd