Search Results for author: Aditya Nori

Found 20 papers, 9 papers with code

Repairing Neural Networks by Leaving the Right Past Behind

no code implementations11 Jul 2022 Ryutaro Tanno, Melanie F. Pradier, Aditya Nori, Yingzhen Li

Prediction failures of machine learning models often arise from deficiencies in training data, such as incorrect labels, outliers, and selection biases.

Continual Learning

Making the Most of Text Semantics to Improve Biomedical Vision--Language Processing

1 code implementation21 Apr 2022 Benedikt Boecking, Naoto Usuyama, Shruthi Bannur, Daniel C. Castro, Anton Schwaighofer, Stephanie Hyland, Maria Wetscherek, Tristan Naumann, Aditya Nori, Javier Alvarez-Valle, Hoifung Poon, Ozan Oktay

We release a new dataset with locally-aligned phrase grounding annotations by radiologists to facilitate the study of complex semantic modelling in biomedical vision--language processing.

Contrastive Learning Language Modelling +4

Active label cleaning for improved dataset quality under resource constraints

1 code implementation1 Sep 2021 Melanie Bernhardt, Daniel C. Castro, Ryutaro Tanno, Anton Schwaighofer, Kerem C. Tezcan, Miguel Monteiro, Shruthi Bannur, Matthew Lungren, Aditya Nori, Ben Glocker, Javier Alvarez-Valle, Ozan Oktay

Imperfections in data annotation, known as label noise, are detrimental to the training of machine learning models and have an often-overlooked confounding effect on the assessment of model performance.

Hierarchical Analysis of Visual COVID-19 Features from Chest Radiographs

1 code implementation14 Jul 2021 Shruthi Bannur, Ozan Oktay, Melanie Bernhardt, Anton Schwaighofer, Rajesh Jena, Besmira Nushi, Sharan Wadhwani, Aditya Nori, Kal Natarajan, Shazad Ashraf, Javier Alvarez-Valle, Daniel C. Castro

Chest radiography has been a recommended procedure for patient triaging and resource management in intensive care units (ICUs) throughout the COVID-19 pandemic.

Management

Secure Medical Image Analysis with CrypTFlow

1 code implementation9 Dec 2020 Javier Alvarez-Valle, Pratik Bhatu, Nishanth Chandran, Divya Gupta, Aditya Nori, Aseem Rastogi, Mayank Rathee, Rahul Sharma, Shubham Ugare

Our first component is an end-to-end compiler from TensorFlow to a variety of MPC protocols.

Cryptography and Security

Alleviating Privacy Attacks via Causal Learning

1 code implementation ICML 2020 Shruti Tople, Amit Sharma, Aditya Nori

Such privacy risks are exacerbated when a model's predictions are used on an unseen data distribution.

Overfitting in Synthesis: Theory and Practice (Extended Version)

no code implementations17 May 2019 Saswat Padhi, Todd Millstein, Aditya Nori, Rahul Sharma

A standard approach to mitigate overfitting in machine learning is to run multiple learners with varying expressiveness in parallel.

Adaptive Neural Trees

1 code implementation ICLR 2019 Ryutaro Tanno, Kai Arulkumaran, Daniel C. Alexander, Antonio Criminisi, Aditya Nori

Deep neural networks and decision trees operate on largely separate paradigms; typically, the former performs representation learning with pre-specified architectures, while the latter is characterised by learning hierarchies over pre-specified features with data-driven architectures.

General Classification Representation Learning

Semi-Supervised Learning via Compact Latent Space Clustering

no code implementations ICML 2018 Konstantinos Kamnitsas, Daniel C. Castro, Loic Le Folgoc, Ian Walker, Ryutaro Tanno, Daniel Rueckert, Ben Glocker, Antonio Criminisi, Aditya Nori

We present a novel cost function for semi-supervised learning of neural networks that encourages compact clustering of the latent space to facilitate separation.

Clustering

Autofocus Layer for Semantic Segmentation

3 code implementations22 May 2018 Yao Qin, Konstantinos Kamnitsas, Siddharth Ancha, Jay Nanavati, Garrison Cottrell, Antonio Criminisi, Aditya Nori

We propose the autofocus convolutional layer for semantic segmentation with the objective of enhancing the capabilities of neural networks for multi-scale processing.

Brain Tumor Segmentation Organ Segmentation +2

Quantifying Program Bias

no code implementations17 Feb 2017 Aws Albarghouthi, Loris D'Antoni, Samuel Drews, Aditya Nori

With the range and sensitivity of algorithmic decisions expanding at a break-neck speed, it is imperative that we aggressively investigate whether programs are biased.

Decision Making Fairness

Unsupervised domain adaptation in brain lesion segmentation with adversarial networks

1 code implementation28 Dec 2016 Konstantinos Kamnitsas, Christian Baumgartner, Christian Ledig, Virginia F. J. Newcombe, Joanna P. Simpson, Andrew D. Kane, David K. Menon, Aditya Nori, Antonio Criminisi, Daniel Rueckert, Ben Glocker

In this work we investigate unsupervised domain adaptation using adversarial neural networks to train a segmentation method which is more invariant to differences in the input data, and which does not require any annotations on the test domain.

Lesion Segmentation Segmentation +1

Fairness as a Program Property

no code implementations19 Oct 2016 Aws Albarghouthi, Loris D'Antoni, Samuel Drews, Aditya Nori

We explore the following question: Is a decision-making program fair, for some useful definition of fairness?

Decision Making Fairness

Measuring Neural Net Robustness with Constraints

1 code implementation NeurIPS 2016 Osbert Bastani, Yani Ioannou, Leonidas Lampropoulos, Dimitrios Vytiniotis, Aditya Nori, Antonio Criminisi

Despite having high accuracy, neural nets have been shown to be susceptible to adversarial examples, where a small perturbation to an input can cause it to become mislabeled.

Debugging Machine Learning Tasks

no code implementations23 Mar 2016 Aleksandar Chakarov, Aditya Nori, Sriram Rajamani, Shayak Sen, Deepak Vijaykeerthy

Unlike traditional programs (such as operating systems or word processors) which have large amounts of code, machine learning tasks use programs with relatively small amounts of code (written in machine learning libraries), but voluminous amounts of data.

BIG-bench Machine Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.