Search Results for author: Ajitha Rajan

Found 17 papers, 6 papers with code

Fix-Con: Automatic Fault Localization and Repair of Deep Learning Model Conversions between Frameworks

no code implementations22 Dec 2023 Nikolaos Louloudakis, Perry Gibson, José Cano, Ajitha Rajan

Converting deep learning models between frameworks is a common step to maximize model compatibility across devices and leverage optimization features that may be exclusively provided in one deep learning framework.

Fault localization

Hawkeye: Change-targeted Testing for Android Apps based on Deep Reinforcement Learning

no code implementations4 Sep 2023 Chao Peng, Zhengwei Lv, Jiarong Fu, Jiayuan Liang, Zhao Zhang, Ajitha Rajan, Ping Yang

We find that Hawkeye is able to generate GUI event sequences targeting changed functions more reliably than FastBot2 and ARES for the open source Apps and the large commercial App.

reinforcement-learning

Fault Localization for Buggy Deep Learning Framework Conversions in Image Recognition

no code implementations10 Jun 2023 Nikolaos Louloudakis, Perry Gibson, José Cano, Ajitha Rajan

To mitigate such errors, we present a novel approach towards fault localization and repair of buggy deep learning framework conversions, focusing on pre-trained image recognition models.

Fault localization

DeltaNN: Assessing the Impact of Computational Environment Parameters on the Performance of Image Recognition Models

1 code implementation5 Jun 2023 Nikolaos Louloudakis, Perry Gibson, José Cano, Ajitha Rajan

Owing to the increased use of image recognition tasks in safety-critical applications like autonomous driving and medical imaging, it is imperative to assess their robustness to changes in the computational environment, as the impact of parameters like deep learning frameworks, compiler optimizations, and hardware devices on model performance and correctness is not yet well understood.

Autonomous Driving

MutateNN: Mutation Testing of Image Recognition Models Deployed on Hardware Accelerators

1 code implementation2 Jun 2023 Nikolaos Louloudakis, Perry Gibson, José Cano, Ajitha Rajan

On top of that, AI methods such as Deep Neural Networks (DNNs) are utilized to perform demanding, resource-intensive and even safety-critical tasks, and in order to effectively increase the performance of the DNN models deployed, a variety of Machine Learning (ML) compilers have been developed, allowing compatibility of DNNs with a variety of hardware acceleration devices, such as GPUs and TPUs.

Image Classification Model Optimization

Can We Trust Explainable AI Methods on ASR? An Evaluation on Phoneme Recognition

no code implementations29 May 2023 Xiaoliang Wu, Peter Bell, Ajitha Rajan

Explainable AI (XAI) techniques have been widely used to help explain and understand the output of deep learning models in fields such as image classification and Natural Language Processing.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Vaxformer: Antigenicity-controlled Transformer for Vaccine Design Against SARS-CoV-2

1 code implementation18 May 2023 Aryo Pradipta Gema, Michał Kobiela, Achille Fraisse, Ajitha Rajan, Diego A. Oyarzún, Javier Antonio Alfaro

The SARS-CoV-2 pandemic has emphasised the importance of developing a universal vaccine that can protect against current and future variants of the virus.

Protein Language Model

BenchDirect: A Directed Language Model for Compiler Benchmarks

no code implementations2 Mar 2023 Foivos Tsimpourlas, Pavlos Petoumenos, Min Xu, Chris Cummins, Kim Hazelwood, Ajitha Rajan, Hugh Leather

We improve this with BenchDirect which utilizes a directed LM that infills programs by jointly observing source code context and the compiler features that are targeted.

Active Learning Language Modelling

Explanations for Automatic Speech Recognition

no code implementations27 Feb 2023 Xiaoliang Wu, Peter Bell, Ajitha Rajan

We address quality assessment for neural network based ASR by providing explanations that help increase our understanding of the system and ultimately help build trust in the system.

Automatic Speech Recognition Explainable Artificial Intelligence (XAI) +4

Exploring Effects of Computational Parameter Changes to Image Recognition Systems

no code implementations1 Nov 2022 Nikolaos Louloudakis, Perry Gibson, José Cano, Ajitha Rajan

On the other hand, model inference time was affected by all environment parameters with changes in hardware device having the most effect.

Autonomous Driving Code Generation

BenchPress: A Deep Active Benchmark Generator

1 code implementation13 Aug 2022 Foivos Tsimpourlas, Pavlos Petoumenos, Min Xu, Chris Cummins, Kim Hazelwood, Ajitha Rajan, Hugh Leather

We develop BenchPress, the first ML benchmark generator for compilers that is steerable within feature space representations of source code.

Active Learning

Vision Checklist: Towards Testable Error Analysis of Image Models to Help System Designers Interrogate Model Capabilities

no code implementations27 Jan 2022 Xin Du, Benedicte Legastelois, Bhargavi Ganesh, Ajitha Rajan, Hana Chockler, Vaishak Belle, Stuart Anderson, Subramanian Ramamoorthy

Robustness evaluations like our checklist will be crucial in future safety evaluations of visual perception modules, and be useful for a wide range of stakeholders including designers, deployers, and regulators involved in the certification of these systems.

Autonomous Driving

Catch Me If You Can: Blackbox Adversarial Attacks on Automatic Speech Recognition using Frequency Masking

no code implementations3 Dec 2021 Xiaoliang Wu, Ajitha Rajan

We evaluate portability and effectiveness of our techniques using three popular ASRs and two input audio datasets using the metrics - Word Error Rate (WER) of output transcription, Similarity to original audio, attack Success Rate on different ASRs and Detection score by a defense system.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

M3: Semantic API Migrations

no code implementations27 Aug 2020 Bruce Collie, Philip Ginsbach, Jackson Woodruff, Ajitha Rajan, Michael O'Boyle

Our approach is integrated with standard compiler tooling, and we use this integration to evaluate migration opportunities in 9 existing C/C++ applications with over 1MLoC.

Software Engineering

Learning to Encode and Classify Test Executions

no code implementations8 Jan 2020 Foivos Tsimpourlas, Ajitha Rajan, Miltiadis Allamanis

We use the labelled traces to train a neural network (NN) model to learn to distinguish runtime patterns for passing versus failing executions for a given program.

General Classification Specificity

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