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.
Deep learning research framework based on Theano
| Date | Stars |
|---|---|
| 2026-07-31 | 268 |
| 2026-08-01 | 268 |
| 2026-08-06 | 268 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
Theano-Lights ============= Theano-Lights is a research framework based on Theano providing implementation of several recent Deep learning models and a convenient training and test functionality. The models are not hidden and spread out behind layers of abstraction as in most deep learning platforms to enable transparency and flexiblity during learning and research. To run: ``` pip install -r requirements.txt python train.py ``` You can find instructions on how to obtain and prepare the datasets [here](https://github.com/Ivaylo-Popov/Theano-Lights/blob/master/Data%20instructions.txt). #### Included models: * Feedforward neural network (FFN) * Convolutional neural network (CNN) * Recurrent neural networks (RNN) * Variational autoencoder (VAE) * Convolutional Variational autoencoder (CVAE) * Deep Recurrent Attentive Writer (DRAW) * LSTM language model #### Included features: * Batch normalization * Dropout * LSTM, GRU and SCRN recurrent layers * Virtual adversarial training (Miyato et al., 2015) * Contractive cost (Rifai et al., 2011) #### Stochastic gradient descent variants: * SGD with momentum * SGD Langevin dynamics * Rmsprop * Adam * Adam with gradient clipping * Walk-forward learning for non-stationary data (data with concept drift) #### Supervised training on: * MNIST #### Unsupervised training on: * MNIST * Frey Faces * Penn Treebank * text8 #### Other models and features: * Auto-classifier-encoder (Georgiev, 2015) * Radias basis function neural network * Denoising autoencoder with lateral connections #### Work in progress: * Natural neural networks (Desjardins et al., 2015) * Ladder network (Rasmus et al., 2015) * Virtual adversarial training for CNN and RNN Sampling a generative MNIST model developed in this framework. [](https://youtu.be/XGUrvMAVv5g)
Excerpt of 1,919 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:e5839a2d34d9509c, llm:description: 'Deep learning research framework based on Theano'
matched fp:e5839a2d34d9509c, llm:description: 'Deep learning research framework based on Theano'