Predicting the parameters of a neural network without training it

Centre for Advancing Responsible and Ethical AI academic co-director and U of G faculty, Dr. Graham Taylor, will speak about neural networks at the #AIforGood summit hosted by the International Telecommunication Union, the UN's specialized agency for information and communication technologies.

Reducing barriers for deep learning practitioners to develop neural networks is one step towards democratizing deep learning, by making the technology more accessible to smaller players in the field. This AI for Good Discovery will explore the key themes in Graham Taylor’s research around removing barriers for deep learning practitioners who lack the background or resources to work with cutting-edge models that require advanced forms of hardware parallelism. Collaborating with Facebook AI Research (now Meta), his team developed a technique to initialize diverse neural network architectures using a “meta-model”. This research challenges the long-held assumption that gradient-based optimizers are required to train deep neural networks.