MeM-Scales – Memory technologies with multi-scale time constants for neuromorphic architectures

Agrate UNIT, Progetti conclusi

Febbraio 8, 2021

Neural processing in the nervous system occurs naturally over multiple time scales ranging from milliseconds (axonal transmission) to seconds (spoken phrases) and much longer intervals (motor learning).

In MeM-Scales we aim at building a novel class of neuromorphic computing systems that reproduce multi-timescale processing of biological neural systems, for building a novel
class of neuromorphic computing systems that can process efficiently real-world sensory signals and natural time-series data in real-time (e.g. for low-power and always-on IoT and
edge-computing applications that do not need to connect to the cloud), and to demonstrate this with a practical laboratory prototype.

The project consortium is broadly interdisciplinary, joining 9 international
groups (Research centers, Universities and Industry) from material science through microchip design & manufacturing to computational neuroscience and machine learning.

Coordinator: CEA-Leti, France

Participants: IMEC, IMEC-NL, IBM, CNR-IMM, Consejo superior de Investigaciones Científicas (CSIC), University of Zurich, Univ. Groningen, aiCTX AG

Objectives. Our scientific and technological objectives can be summarized
as follows:

To study the theory, and develop algorithmic and architectural innovations for realizing adaptive and robust multi-timescale neural processing on mixed-signal
analog/digital neuromorphic processors comprising both volatile and non-volatile memory devices to implement the synaptic circuits and TFT-based neurons.
To develop novel hardware technologies that
support on-chip learning with multiple time constants, both for synapses (volatile memory option combined with non-volatile memory, Electrochemical metallization, vacancy-type oxide-based memories, and Phase Change Memory), and neurons (TFT option
exploration, plus integration with other devices).
To study and develop an ultra-low-power, scalable and highly configurable neuromorphic computing processor capable of online, life-long learning for
personalized neural learning and adaptation algorithms.
To validate and demonstrate the project developments on realistic fully personalized edge application cases (by both simulation and board
prototyping).