Rajeev V. Rikhye, Ph. D.

Senior Researcher and ML Engineer, Google DeepMind

rvrikhye [AT] gmail.com

Bio

I am passionate about applied AI. I am a Machine Learning Engineer and Researcher at Google DeepMind where I am working on improving the factuality and freshness of Gemini, Google's Large Language Models to ensure that users always get the most factually accurate information.

Prior to joining DeepMind, I was a researcher in the Health AI team of Google Research where I developed an launched a new dermatology experience on Google Lens, which allows users to better understand their skin conditions. Working with Fitbit, I helped to lead efforts to develop a personalized health assistant.

I am a trained computational neuroscientist. I was a Researcher at Vicarious AI studying neuroscience-inspired computer vision algorithms for object recognition and . I hold a Ph. D in Systems Neuroscience from MIT and a M. Eng. in Biomedical Engineering from Imperial College London.

My research interests lie at the intersection of Computational Neuroscience, Machine Learning and Embedded Systems. Specifically, I hope to one day develop intelligent agents that see, act and, in turn, solve real-world problems.

I am originally from Singapore. In my spare time, I am a dog-dad to Tintin the Sheepadoodle. I am a huge AFOL and am rapidly running out of display space.

Most recent publications on Google Scholar.

Neuroscience Publications

Reinforcement-guided learning in frontal neocortex: emerging computational concepts

Abhishek Banerjee, Rajeev V Rikhye, Adam Marblestone

Current Opinion in Behavioral Sciences 328, 2021

Clone-structured graph representations enable flexible learning and vicarious evaluation of cognitive maps

Dileep George, Rajeev V Rikhye, Nishad Gothoskar, J Swaroop Guntupalli, Antoine Dedieu, Miguel Lázaro-Gredilla

Nature Communications 12(1), 2021

PDF

Learning cognitive maps for vicarious evaluation

RV Rikhye, N Gothoskar, JS Guntupalli, A Dedieu, M Lazaro-Gredilla, D George

Cerebral Cortex 30(2) 2020

Prefrontal computation as active inference

T. Parr RV Rikhye, MM Halassa, K. Friston

Cerebral Cortex 30(2) 2020

PDF

Thalamic regulation of switching between cortical representations enables cognitive flexibility

RV Rikhye, A Gilra, MM Halassa

Nature Neuroscience 21(12) 2018

Toward an integrative theory of thalamic function

RV Rikhye, RD Wimmer, MM Halassa

Annual Reviews in Neuroscience 41 2018

PDF

Reliable sensory processing in mouse visual cortex through inhibitory interactions between Somatostatin and Parvalbumin interneurons

RV Rikhye, M Yildirim, V Breton-Provencher, M Hu, M Sur

The Journal of Neuroscience 41 (42), 2021

Jointly reduced inhibition and excitation underlies circuit-wide changes in cortical processing in Rett syndrome

A Banerjee, RV Rikhye, V Breton-Provencher, C Li, K, Li, M Sur

Proceedings of the National Academy of Sciences 113 (46) 2016

PDF

Spatial Correlations in Natural Scenes Modulate Response Reliability in Mouse Visual Cortex

RV Rikhye, M Sur

The Journal of Neuroscience 35(43) 2015

PDF

Health AI Publications

Differences Between Patient and Clinician-Taken Images: Implications for Virtual Care of Skin Conditions

RV Rikhye, et al.

Mayo Clinic Proceedings: Digital Health 2 (1), 2024

PDF

Closing the AI generalization gap by adjusting for dermatology condition distribution differences across clinical settings

RV Rikhye, et al.

Lancet eBiomedicine

Speech Publications

Personalized keyphrase detection using speaker and environment information

RV Rikhye, Quan Wang, Qiao Liang, Yanzhang He, Ding Zhao, Arun Narayanan, Ian McGraw

INTERSPEECH 2021

Multi-user VoiceFilter-Lite via attentive speaker embedding

RV Rikhye, Quan Wang, Qiao Liang, Yanzhang He, Ian McGraw

IEEE ASRU 2021

Closing the gap between single-user and multi-user voicefilter-lite

RV Rikhye, Quan Wang, Qiao Liang, Yanzhang He, Ian McGraw

IEEE ASRU 2022

Personal VAD 2.0: Optimizing personal voice activity detection for on-device speech recognition

Shaojin Ding, Rajeev Rikhye, Qiao Liang, Yanzhang He, Quan Wang, Arun Narayanan, Tom O'Malley, Ian McGraw

INTERSPEECH 2022

Conditional Conformer: Improving Speaker Modulation For Single And Multi-User Speech Enhancement

Tom O’Malley, Shaojin Ding, Arun Narayanan, Quan Wang, Rajeev Rikhye, Qiao Liang, Yanzhang He, Ian McGraw

ICASSP 2022

Vitæ

Full Resume in PDF.

Acknowledgements

This website uses the website design and template by Martin Saveski