Code

In the SMALL project we are dedicated to sharing our knowledge with the scientific community and with the wider public. Hence, we regularly publicly release the code, developed as product of the project’s various interesting tasks. On this page you can find all the SMALL open-source code and all the corresponding documentation.

ReckOn

A Spiking RNN Processor Enabling On-Chip Learning over Second-Long Timescales

"ReckOn is a spiking recurrent neural network (RNN) processor enabling on-chip learning over second-long timescales based on a modified version of the e-prop algorithm."

CLICK HERE FOR THE CODE

Published at ISSCC 2022 !

OSTL

Online Spatio-Temporal Learning in Deep Neural Networks

"For shallow networks, OSTL is gradient-equivalent to BPTT enabling for the first time online training of SNNs with BPTT-equivalent gradients. In addition, the proposed formulation unveils a class of SNN architectures trainable online at low time complexity. Moreover, we extend OSTL to a generic form, applicable to a wide range of network architectures, including networks comprising long short-term memory (LSTM) and gated recurrent units (GRU). We demonstrate the operation of our algorithm on various tasks from language modelling to speech recognition and obtain results on par with the BPTT baselines. The proposed algorithm provides a framework for developing succinct and efficient online training approaches for SNNs and in general deep RNNs."

CLICK HERE FOR THE CODE

Py-EDScorbotTool

This tool allows for the use of EDScorbot, a robotic arm with an Event-Driven controller based on FPGAs.

"It is written in Python and serves as a substitute of ATCEDScorbotConfig filter in jAER."

CLICK HERE FOR THE CODE

More to come...