R
Rishi Sharma
Researcher at University of California, Berkeley
Publications - 6
Citations - 524
Rishi Sharma is an academic researcher from University of California, Berkeley. The author has contributed to research in topics: Deep learning & Hyperparameter optimization. The author has an hindex of 4, co-authored 6 publications receiving 386 citations.
Papers
More filters
Posted Content
A Note on the Inception Score
Shane Barratt,Rishi Sharma +1 more
TL;DR: New insights are provided into the Inception Score, a recently proposed and widely used evaluation metric for generative models, and it is demonstrated that it fails to provide useful guidance when comparing models.
Posted Content
Weakly-Supervised Deep Learning of Heat Transport via Physics Informed Loss
TL;DR: This work demonstrates that knowledge of the partial differential equations governing a system can be encoded into the loss function of a neural network via an appropriately chosen convolutional kernel, and demonstrates that this method can be used to speed up exact calculation of the solution to the differential equations via finite difference.
Posted Content
Improved Training with Curriculum GANs
TL;DR: Curriculum GANs is introduced, a curriculum learning strategy for training Generative Adversarial Networks that increases the strength of the discriminator over the course of training, thereby making the learning task progressively more difficult for the generator.
Posted Content
Deep Learning Phase Segregation.
TL;DR: This work presents a data-driven approach for the learning, modeling, and prediction of phase segregation, where a direct mapping between an initially dispersed, immiscible binary fluid and the equilibrium concentration field is learned by conditional generative convolutional neural networks.
Posted Content
Optimizing for Generalization in Machine Learning with Cross-Validation Gradients.
Shane Barratt,Rishi Sharma +1 more
TL;DR: This paper shows that the cross- validation risk is differentiable with respect to the hyperparameters and training data for many common machine learning algorithms, including logistic regression, elastic-net regression, and support vector machines, and proposes a cross-validation gradient method (CVGM) for hyperparameter optimization.