CNTK and Deep Reinforcement Learning

We will be hosting our next Mulhouse Machine Learning Meetup at the IUT Mulhouse with a special guest.

Morgan Funtowicz will be sharing with us via Skype some insights about the implementation of Reinforcement Learning agents and answering questions about Deep Learning models and capabilities of the Microsoft Cognitive Toolkit (CNTK), being some of those:

Highly optimized, built-in components as:

• Components can handle multi-dimensional dense or sparse data from Python, C++ or BrainScript
• FFN, CNN, RNN/LSTM, Batch normalization, Sequence-to-Sequence with attention and more- Reinforcement learning, generative adversarial networks, supervised and unsupervised learning
• Ability to add new user-defined core-components on the GPU from Python- Automatic hyperparameter tuning
• Built-in readers optimized for massive datasets
• Parallelism with accuracy on multiple GPUs/machines via 1-bit SGD and Block Momentum
• Memory sharing and other built-in methods to fit even the largest models in GPU memory

Morgan Funtowicz is a French AI lover and passionate about Machine Learning. He did his final engineering school internship at Microsoft France working on Deep Learning & CNTK. After this, he moved to the Machine Intelligence and Perception group at Microsoft Research Cambridge (UK). Currently working on Project Malmo and CNTK helping researchers build next generation AI.