Towards efficient end-to-end speech recognition with biologically-inspired neural networks

no code implementations • 4 Oct 2021 • Thomas Bohnstingl, Ayush Garg, Stanisław Woźniak, George Saon, Evangelos Eleftheriou, Angeliki Pantazi

Automatic speech recognition (ASR) is a capability which enables a program to process human speech into a written form.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Online Spatio-Temporal Learning in Deep Neural Networks

1 code implementation • 24 Jul 2020 • Thomas Bohnstingl, Stanisław Woźniak, Wolfgang Maass, Angeliki Pantazi, Evangelos Eleftheriou

For shallow networks, OSTL is gradient-equivalent to BPTT enabling for the first time online training of SNNs with BPTT-equivalent gradients.

Language Modelling speech-recognition +1

Neuromorphic Hardware learns to learn

no code implementations • 15 Mar 2019 • Thomas Bohnstingl, Franz Scherr, Christian Pehle, Karlheinz Meier, Wolfgang Maass

In contrast, the hyperparameters and learning algorithms of networks of neurons in the brain, which they aim to emulate, have been optimized through extensive evolutionary and developmental processes for specific ranges of computing and learning tasks.

Deep learning incorporating biologically-inspired neural dynamics

1 code implementation • 17 Dec 2018 • Stanisław Woźniak, Angeliki Pantazi, Thomas Bohnstingl, Evangelos Eleftheriou

Neural networks have become the key technology of artificial intelligence and have contributed to breakthroughs in several machine learning tasks, primarily owing to advances in deep learning applied to Artificial Neural Networks (ANNs).

Language Modelling