Misha Denil
48 works · 3,330 citations · h-index 19
Top works
- Predicting Parameters in Deep Learning
- Learning Where to Attend with Deep Architectures for Image Tracking
- Deep Fried Convnets
- Learning to learn by gradient descent by gradient descent
- Learning to Navigate in Complex Environments
- Deep Fried Convnets
- From Group to Individual Labels Using Deep Features
- Modelling, Visualising and Summarising Documents with a Single Convolutional Neural Network
- Narrowing the Gap: Random Forests In Theory and In Practice
- Noisy Activation Functions
- Learning to Learn without Gradient Descent by Gradient Descent
- Overlap versus Imbalance
- Extraction of Salient Sentences from Labelled Documents
- Learned Optimizers that Scale and Generalize
- Deep Multi-Instance Transfer Learning
- Consistency of Online Random Forests
- Learning to Perform Physics Experiments via Deep Reinforcement Learning
- Scaling data-driven robotics with reward sketching and batch reinforcement learning
- Learning to Learn for Global Optimization of Black Box Functions.
- Hyperbolic Attention Networks