Larq Compute Engine: Design, Benchmark, and Deploy State-of-the-Art Binarized Neural Networks

1 code implementation • 18 Nov 2020 • Tom Bannink, Arash Bakhtiari, Adam Hillier, Lukas Geiger, Tim de Bruin, Leon Overweel, Jelmer Neeven, Koen Helwegen

We introduce Larq Compute Engine, the world's fastest Binarized Neural Network (BNN) inference engine, and use this framework to investigate several important questions about the efficiency of BNNs and to design a new state-of-the-art BNN architecture.

Vision-based Navigation Using Deep Reinforcement Learning

1 code implementation • 8 Aug 2019 • Jonáš Kulhánek, Erik Derner, Tim de Bruin, Robert Babuška

However, the application of deep RL to visual navigation with realistic environments is a challenging task.

Efficient Neural Network reinforcement-learning +2