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*, Engelhardt B E —
Pacific Symposium on Biocomputing (PSB 2019) - Accepted for oral presentation
Laboratory testing is an integral tool in the management of patient care in hospitals, particularly in intensive care units (ICUs). There exists an inherent trade-off in the selection and timing of lab tests between considerations of the expected utility in clinical decision-making of a given test at a specific time, and the associated cost or risk it poses to the patient [..] To this end, we develop and extend principles of Pareto optimality to improve the selection of actions based on multiple reward function components while respecting typical procedural considerations and prioritization of clinical goals in the ICU. Our experiments show that we can estimate a policy that reduces the frequency of lab tests and optimizes timing to minimize information redundancy [..]
| arxiv | proceedings |
Prasad N, Cheng L-F, Chivers C, Draugelis M, Engelhardt B E —
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 [..] 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 [..]
| arxiv | proceedings | presentation |
Williams W, Prasad N, Mrva D, Ash T, Robinson T —
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 [..] 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.
| arxiv | proceedings |
Peer-Reviewed Workshops and Presentations
Defining Admissible Rewards for High-Confidence Policy Evaluation
- NeurIPS 2019 Workshop on Safety and Robustness in Decision Making
- “Do the right thing” : Machine Learning and Causal Inference for Improved Decision Making | arxiv |
- 3rd Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM) 2017 - University of Michigan, Ann Arbor, USA
- Women in Machine Learning Workshop (WiML) 2016 - Barcelona, Spain
- UKSpeech Conference 2015 - University of East Anglia, UK
- Our recent paper on learning an ordering policy for lab tests in intensive care was featured here.
- Our participation in the 2017 Amazon Alexa Prize received coverage both within Princeton, and in an interview with CNet: "A chat with Pixie, Princeton University's socialbot" .
- Check out Professor Barbara Engelhardt's talk at TEDxBoston, on various recent and ongoing work from our lab!
You can find my full CV here.
To get in touch, email me at np6 [at] princeton [dot] edu. You can also find me on: