Digests ยป 159

this week's favorite

HyperLib: Deep learning in the Hyperbolic space

This library implements common Neural Network components in the hypberbolic space (using the Poincare model). The implementation of this library uses Tensorflow as a backend and can easily be used with Keras and is meant to help Data Scientists, Machine Learning Engineers, Researchers and others to implement hyperbolic neural networks.

Predictive coding can do exact backpropagation on any neural network

Intersecting neuroscience and deep learning has brought benefits and developments to both fields for several decades, which help to both understand how learning works in the brain, and to achieve the state-of-the-art performances in different AI benchmarks. Backpropagation (BP) is the most widely adopted method for the training of artificial neural networks, which, however, is often criticized for its biological implausibility (e.g., lack of local update rules for the parameters).

ArXiv Miner: Toolkit for mining research papers on CS ArXiv

arxiv-miner is a quick handy library that helps power Sci-Genie. Sci-Genie is a search engine for quickly searching through full text of papers on CS ArXiv. arxiv-miner helps extract and parse LaTeX documents from CS ArXiv. It also supports storage and search of those parsed documents using Elasticsearch. The library can be applicable for all other domains like Math, Physics, Biology etc.

AndroidEnv: The android learning environment

We introduce AndroidEnv, an open-source platform for Reinforcement Learning (RL) research built on top of the Android ecosystem. AndroidEnv allows RL agents to interact with a wide variety of apps and services commonly used by humans through a universal touchscreen interface. Since agents train on a realistic simulation of an Android device, they have the potential to be deployed on real devices. In this report, we give an overview of the environment, highlighting the significant features it provides for research, and we present an empirical evaluation of some popular reinforcement learning agents on a set of tasks built on this platform.

Transfer learning can boost code autocompletion accuracy by over 50%

In a paper, a research team from Facebook demonstrates how transfer learning can enable pre-training on non-IDE, non-autocompletion, and different-language example code sequences before fine-tuning on the autocompletion prediction task. The proposed method improves model accuracy by more than 50 percent on small fine-tuning datasets and over 10 percent on 50k labeled examples.