Abstract: Autoencoder models of source code are an emerging alternative to autoregressive ... We propose a structured Variational Auto-Encoder based on TreeLSTM that operates directly on the AST. We ...

This repository provides code to accompany the paper: Greener JG, Moffat L and Jones DT, Design of metalloproteins and novel protein folds using variational autoencoders, Scientific Reports 8:16189, ...

The Variational Autoencoder model is a neural network that provides collaborative ... (TF-AMP), which enables mixed precision training without any changes to the code-base by performing automatic ...

Writing computationally efficient code is a skill everyone has wanted to master since they first wrote Hello World on their computers. Thankfully, Researchers at Google and Georgia Tech have found a ...

wrapping or unwrapping code in functions, adjusting loop bounds, etc. The team proposes an explicit and interpretable discrete variational auto-encoder model for generating efficiency-improving code ...

Figure 1: Generating Synthetic Data Using a Variational Autoencoder This article assumes you have an intermediate or better familiarity with a C-family programming language, preferably Python, and a ...