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…

Imke’s final work was published in Nature Communications

Imke’s paper was published in Nature Communications! In this work Imke developed a smart robotic gripper equipped with a small-scale organic neuromorphic circuit. In her final work she developed the neuromorphic robotic gripper to locally integrate and adaptively process multimodal sensory stimuli, enabling it to interact intelligently with its surroundings and learning to avoid dangerous objects. Find, and read, the open access paper here: https://www.nature.com/articles/s41467-024-48881-2 

New paper in Nature Communications

Eveline’s and Gianmaria’s paper was published in Nature Communications! In this work Eveline, Gianmaria and co-authors developed a modular spiking circuit that is able to encode light input into spikes that are further modulated by chemical synapses which are tuned by the amount of neurotransmitter available. With this work we open up a path to replicate the interdependent functions of receptors, neurons, and synapses towards retina-inspired sensory coding. Find, and read, the open access paper here: https://www.nature.com/articles/s41467-024-47226-3