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.
Neural Symbolic Machines is a framework to integrate neural networks and symbolic representations using reinforcement learning, with applications in program synthesis and semantic parsing.
| Date | Stars |
|---|---|
| 2026-07-24 | 385 |
| 2026-07-25 | 385 |
| 2026-07-28 | 385 |
| 2026-07-30 | 385 |
| 2026-07-31 | 385 |
| 2026-08-06 | 385 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Introduction ## Neural Symbolic Machines (NSM) Neural Symbolic Machines is a framework to integrate neural networks and symbolic representations using reinforcement learning. <div align="middle"><img src="https://github.com/crazydonkey200/neural-symbolic-machines/blob/master/images/nsm.png" width="80%" ></div> ## Applications The framework can be used to learn semantic parsing and program synthesis from weak supervision (e.g., question-answer pairs), which is easier to collect and more flexible than full supervision (e.g., question-program pairs). Applications include virtual assistant, natural language interface to database, human-robot interaction, etc. It has been used to <a href="https://arxiv.org/abs/1611.00020">learn semantic parsers on Freebase<a> and <a href="https://arxiv.org/abs/1807.02322">natural language interfaces to database tables<a>. <div align="middle"><img src="https://github.com/crazydonkey200/neural-symbolic-machines/blob/master/images/ap.png" width="80%"></div> ## Memory Augmented Policy Optimization (MAPO) We use <a href="https://arxiv.org/abs/1807.02322">Memory Augmented Policy Optimization (MAPO)</a> to train NSM. It is a new policy optimization method that uses a memory buffer of promising trajectories to accelerate and stabilize policy gradient training. It is well suited for deterministic environments with discrete actions, for example, structured prediction, combinatorial optimization, program synthesis, etc. <div align="middle"><img src="https://github.com/crazydonkey200/neural-symbolic-machines/blob/master/images/mapo.png" width="80%"></div> ## Distributed Actor-Learner Architecture Our implementation uses a distributed actor-learner architecture that utilizes multiple CPUs and GPUs for scalable training, similar to the one introduced in <a href="https://arxiv.org/abs/1802.01561">the IMPALA paper from DeepMind</a>. <div align="middle"><img src="https://github.com/crazydonkey200/neural-symbolic-machines/blob/master/images/al.png" width="80%"></div> # Dependencies - Python 2.7 - TensorFlow>=1.7 - Other required packages are summarized in `requirements.txt`. # Quick start ## Setup AWS instance Start a g3.8xlarge instance with “Deep Learning AMI (Ubuntu) Version 10.0” image. (The experiments are conducted using this type of instance and image, you will need to adjust the configurations in scripts to run on other instances.) Open port (for example, 6000-6010) in the security group for tensorboard. Instructions: https://docs.aws.amazon.com/dlami/latest/devguide/tutorial-tensorboard.html ssh into the instance. ## Download the data and install the dependencies ``` mkdir ~/projects cd ~/projects/ git clone https://github.com/crazydonkey200/neural-symbolic-machines.git cd ~/projects/neural-symbolic-machines/ ./aws_setup.sh ``` Note that this downloads the preprocessed dataset, if you want to replicate the preprocessing and/or adapt the code to a similar dataset, here's a great [manual / summary](https://github.com/ShaharKSegal/MAPO-Reproducing-Manual) created by [ShaharKSegal](https://github.com/ShaharKSegal). ## Running experiments and monitor with tensorboard ### Start WikiTable experiment ``` screen -S wtq source activate tensorflow_p27 cd ~/projects/neural-symbolic-machines/table/wtq/ ./run.sh mapo your_experiment_name ``` This script trains the model for 30k steps and evaluates the checkpoint with the highest dev accuracy on the test set. It takes about 2.5 hrs to finish. All the data about this experiment will be saved in `~/projects/data/wikitable/output/your_experiment_name`, and the evaluation result would be saved in `~/projects/data/wikitable/output/eval_your_experiment_name`. You could also evaluate a trained model on the dev set or test set using ``` ./eval.sh your_experiment_name dev ./eval.sh your_experiment_name test ``` ### Start tensorboard to monitor WikiTable experiment ``` screen -S tb source activate tensorflow_p27 cd ~/projects/data/wikitable/ t
Excerpt of 6,614 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:b79ec0e616480e6c, topic:reinforcement-learning, topic:deep-reinforcement-learning, desc:reinforcement learning
matched fp:b79ec0e616480e6c, topic:deep-learning, topic:tensorflow