Search Results

OptNet: Differentiable Optimization as a Layer in Neural Networks

6 code implementations ICML 2017

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.

Bilevel Optimization

Shoulder Physiotherapy Exercise Recognition: Machine Learning the Inertial Signals from a Smartwatch

1 code implementation5 Feb 2018

Significance: This proof of concept study demonstrates the technical feasibility of a smartwatch device and supervised machine learning approach to more easily monitor and assess the at-home adherence of shoulder physiotherapy exercise protocols.

Human-Computer Interaction I.2.1

Scenic: A Language for Scenario Specification and Scene Generation

2 code implementations25 Sep 2018

We propose a new probabilistic programming language for the design and analysis of perception systems, especially those based on machine learning.

Probabilistic Programming Scene Generation +1

Neural Architecture Search with Bayesian Optimisation and Optimal Transport

1 code implementation NeurIPS 2018

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.

Bayesian Optimisation BIG-bench Machine Learning +2

Scenic: A Language for Scenario Specification and Data Generation

2 code implementations13 Oct 2020

We design a domain-specific language, Scenic, for describing scenarios that are distributions over scenes and the behaviors of their agents over time.

Probabilistic Programming Synthetic Data Generation

Just-in-Time Code Duplicates Extraction

1 code implementation7 Feb 2023

The results show that developers tend to appreciate the idea of the approach and are satisfied with various aspects of the plugin's operation.

Software Engineering

Protein identification with deep learning: from abc to xyz

1 code implementation8 Oct 2017

We combine two modules de novo sequencing and database search into a single deep learning framework for peptide identification, and integrate de Bruijn graph assembly technique to offer a complete solution to reconstruct protein sequences from tandem mass spectrometry data.

de novo peptide sequencing

Open-Ended Visual Question-Answering

1 code implementation9 Oct 2016

This thesis report studies methods to solve Visual Question-Answering (VQA) tasks with a Deep Learning framework.

Question Answering Sentence +3

DeepDrug3D: Classification of ligand-binding pockets in proteins with a convolutional neural network

1 code implementation Plos Computational Biology 2019

Interestingly, the analysis of strongly discriminative regions of binding pockets reveals that this high classification accuracy arises from learning the patterns of specific molecular interactions, such as hydrogen bonds, aromatic and hydrophobic contacts.

Benchmarking Specificity