Projects

Reinforcement Learning

• Posterior Sampling for Deep Reinforcement Learning [code]
• Multi-Source Transfer Learning for Deep Model-Based Reinforcement Learning [code]
• Human-Level Game-Playing Agents for Lines of Action using Temporal Difference Learning [code]

Natural Language Processing

• Detecting Machine Translation using Transformers [code]
• Music Genre Classification using Recurrent Neural Networks [code]

Computer Vision

• Synthesizing Images of Cats using Generative Adverserial Networks [code]
• Improving Generative Grasping using Mixed Autoencoders [code]
• Large Scale Car Part Classification [private code, industrial]