code2vec: Learning Distributed Representations of Code

26 Mar 20187 code implementations

We demonstrate the effectiveness of our approach by using it to predict a method's name from the vector representation of its body.

Pyro: Deep Universal Probabilistic Programming

18 Oct 20181 code implementation

Pyro is a probabilistic programming language built on Python as a platform for developing advanced probabilistic models in AI research.


mlpack 3: a fast, flexible machine learning library

Journal of Open Source Software 2018 1 code implementation

In the past several years, the field of machine learning has seen an explosion of interest and excitement, with hundreds or thousands of algorithms developed for different tasks every year.

OptNet: Differentiable Optimization as a Layer in Neural Networks

ICML 2017 4 code implementations

This paper presents OptNet, a network architecture that integrates optimization problems (here, specifically in the form of quadratic programs) as individual layers in larger end-to-end trainable deep networks.

Provable defenses against adversarial examples via the convex outer adversarial polytope

ICML 2018 7 code implementations

We propose a method to learn deep ReLU-based classifiers that are provably robust against norm-bounded adversarial perturbations on the training data.


DeepDSL: A Compilation-based Domain-Specific Language for Deep Learning

9 Jan 20171 code implementation

In this paper, we present DeepDSL, a domain specific language (DSL) embedded in Scala, that compiles deep networks written in DeepDSL to Java source code.

DeepCoder: Learning to Write Programs

7 Nov 20163 code implementations

We develop a first line of attack for solving programming competition-style problems from input-output examples using deep learning.


Neural Architecture Search with Bayesian Optimisation and Optimal Transport

NeurIPS 2018 1 code implementation

A common use case for BO in machine learning is model selection, where it is not possible to analytically model the generalisation performance of a statistical model, and we resort to noisy and expensive training and validation procedures to choose the best model.


Learning to Prove Theorems via Interacting with Proof Assistants

21 May 20191 code implementation

Proof assistants offer a formalism that resembles human mathematical reasoning, representing theorems in higher-order logic and proofs as high-level tactics.


BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning

NeurIPS 2019 1 code implementation

We develop BatchBALD, a tractable approximation to the mutual information between a batch of points and model parameters, which we use as an acquisition function to select multiple informative points jointly for the task of deep Bayesian active learning.