memscales.png

The Institute for Microelectronics and Microsystems of the National Research Council (CNR) opens a Post-Doc Position funded through the European Horizon 2020 ICT project MeM-Scales «Memory technologies with multi-scale time constants for neuromorphic architectures» (contract number n. 871371).

 

MeM-Scales Project Description

The overall objective of the MeM-Scales project (https://memscales.eu/) is the joint co-development of a novel class of algorithms, devices and circuits that reproduce multi-timescale processing of biological neural systems. Indeed, biological brains can integrate information across timescales that span many orders of magnitude, from millisecond visual information processing to many years of long-term memory consolidation and forgetting. In MeM-Scales, we aim at building a novel class of neuromorphic computing systems that can integrate temporal information over multiple timescales and 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. The consortium will lead a cross-disciplinary effort towards the fabrication of an innovative hardware/ software platform as a basis for future products which combine extreme power efficiency with robust cognitive computing capabilities.

 

Open Position description

 

Within the MeM-Scales project, the group at CNR-IMM, Unit of Agrate Brianza (Italy) (www.mdm.imm.cnr.it) will target in collaboration with international partners the development of novel memory and device technologies, with focus on RRAM and PCM, supporting on-chip learning over multiple timescales. In this framework, we have opened a post- doc position under the scientific supervision of Dr. Sabina Spiga.

System-level simulation of spiking neural networks. The focus will be the development of system level simulation of spiking neural networks implementing the information integration over multiple timescales. Models for neurons and synapses will be developed on the base of experimental data from real hardware. The activity will serve: (i) as a guide for the development of synapse and neuron devices and circuits, and (ii) to guide the tuning of synapse and neuron parameters for specific applications. Simulations and hardware development will be performed in a close loop and continuous feedback. The post-doc will work in close collaborations with international partners and short exchange visits are planned.

Additional Information and specific requirements for the open positions

Institution: CNR-IMM, Unit of Agrate Brianza, Italy

Level: PhD degree

Contract: 1 year, renewable to project duration

Fields: Physics, Electrical Engineering, Computer Engineering, Artificial intelligence, Neuromorphic computing or related disciplines

Experience: in neural network simulation, including memristive devices with focus on RRAM and PCM. Strong motivation to work in the field of neuromorphic computing.

Application: through public selection which is posted on the CNR web site (https://bandi.urp.cnr.it/doc-assegni/documentazione/10444_DOC_IT.pdf). The call is in Italian. Interested candidates can send an e-mail with a CV to the following contact for further information or for any support for the application fulfillment. The planned starting date is within the first months of 2021, depending on candidate availability and required time for selection procedures.

Contact: Sabina Spiga, CNR-IMM-Agrate Brianza, sabina.spiga@mdm.imm.cnr.it