In 2013, I graduated from the University of Cambridge in Information and Computer Engineering (BA, MEng). Following this, I was with a start-up for two years, working on the research and development of speech recognition software.
My current research interests are primarily in machine learning methods motivated by clinical medicine, spanning reinforcement learning, time series modelling, natural language processing and knowledge representation.
Prasad N, Cheng L-F, Chivers C, Draugelis M, Engelhardt B E, "A Reinforcement Learning Approach to Weaning of Mechanical Ventilation in Intensive Care Units", Conference on Uncertainty in Artificial Intelligence (UAI 2017) - Accepted for plenary presentation.
The management of invasive mechanical ventilation, and the regulation of sedation and analgesia during ventilation, constitutes a major part of the care of patients admitted to intensive care units. Both prolonged dependence on mechanical ventilation and premature extubation are associated with increased risk of complications and higher hospital costs, but clinical opinion on the best protocol for weaning patients off of a ventilator varies. This work aims to develop a decision support tool that uses available patient information to predict time-to-extubation readiness and to recommend a personalized regime of sedation dosage and ventilator support. To this end, we use off-policy reinforcement learning algorithms to determine the best action at a given patient state from sub-optimal historical ICU data. We compare treatment policies from fitted Q-iteration with extremely randomized trees and with feedforward neural networks, and demonstrate that the policies learnt show promise in recommending weaning protocols with improved outcomes, in terms of minimizing rates of reintubation and regulating physiological stability.
Williams W, Prasad N, Mrva D, Ash T, Robinson T, "Scaling Recurrent Neural Network Language Models" IEEE International Conference on Acoustics, Speech & Signal Processing (ICASSP 2015)
This paper investigates the scaling properties of Recurrent Neural Network Language Models (RNNLMs). We discuss how to train very large RNNs on GPUs and address the questions of how RNNLMs scale with respect to model size, training-set size, computational costs and memory. Our analysis shows that despite being more costly to train, RNNLMs obtain much lower perplexities on standard benchmarks than n-gram models. We train the largest known RNNs and present relative word error rates gains of 18% on an ASR task. We also present the new lowest perplexities on the recently released billion word language modelling benchmark, 1 BLEU point gain on machine translation and a 17% relative hit rate gain in word prediction.
Attached here is my CV.
To get in touch, email me at np6 [at] princeton [dot] edu. You can also find me on: