EMBODEAI Proposal Granted

The EASI Exploratory Multisciplinary A.I. Research (EMDAIR) proposal EMBODEAI: Towards Embodied AI for Continuous Humin-Like Learning proposal was granted. Project Description: State-of-the-art (deep) reinforcement learning systems, for all their fantastic achievements, struggle in real-world tasks that are trivial for humans, especially those involving physical interactions. At the same time these systems consume excessive power for training and operation. That is because they are inefficient with their model representations (many parameters) and their data (big data and many trials for training). Read more

New paper in Science Advances

Eveline’s and Tim’s paper on Hardware implementation of backpropagation using progressive gradient descent for in situ training of multilayer neural networks is now out in Science Advances. The highly predictable tuning characteristics of organic EC-RAM allow us to now train multilayer artificial neural networks directly in hardware.  First authors Eveline Van Doremaele and Tim Stevens found a way to overcome the energy-inefficient storing of the partial derivative of the weights digitally, by sequentially updating each layer in the network directly Read more