N
Nikhil Naik
Researcher at Salesforce.com
Publications - 64
Citations - 5289
Nikhil Naik is an academic researcher from Salesforce.com. The author has contributed to research in topics: Computer science & Artificial neural network. The author has an hindex of 25, co-authored 55 publications receiving 3562 citations. Previous affiliations of Nikhil Naik include Harvard University & College of Engineering, Pune.
Papers
More filters
Posted Content
Designing Neural Network Architectures using Reinforcement Learning
TL;DR: MetaQNN as discussed by the authors is a meta-modeling algorithm based on reinforcement learning to automatically generate high-performing CNN architectures for a given learning task, where the learning agent is trained to sequentially choose CNN layers using $Q$-learning with an $\epsilon$-greedy exploration strategy and experience replay.
Proceedings Article
Designing Neural Network Architectures using Reinforcement Learning
TL;DR: MetaQNN is introduced, a meta-modeling algorithm based on reinforcement learning to automatically generate high-performing CNN architectures for a given learning task that beat existing networks designed with the same layer types and are competitive against the state-of-the-art methods that use more complex layer types.
Proceedings ArticleDOI
Streetscore -- Predicting the Perceived Safety of One Million Streetscapes
TL;DR: The predictive power of commonly used image features is studied using support vector regression, finding that Geometric Texton and Color Histograms along with GIST are the best performers when it comes to predict the perceived safety of a streetscape.
Journal ArticleDOI
Deep learning-enabled medical computer vision.
Andre Esteva,Katherine Chou,Serena Yeung,Nikhil Naik,Ali Madani,Ali Mottaghi,Yun Liu,Eric J. Topol,Jeffrey Dean,Richard Socher +9 more
TL;DR: In this paper, the authors survey recent progress in the development of modern computer vision techniques-powered by deep learning-for medical applications, focusing on medical imaging, medical video, and clinical deployment.
Proceedings Article
Accelerating Neural Architecture Search using Performance Prediction
TL;DR: The authors proposed an early stopping method for hyperparameter optimization and meta-modeling, which obtains a speedup of a factor up to 6x in both hyper-parameter optimisation and meta modeling.