Deep learning and transformers AI Seminar Series

Talk presented by Dr Kasim Terzic, followed by a group discussion. This lecture will give a brief overview of deep learning and how it relates to modern AI architectures such as transformers. We will look how deep neural networks can act as universal function approximators, and how this can enable them to perform tasks such as compression, semantic embedding, and next token prediction, techniques behind many of today's advanced AI algorithms.

The AI Seminar Series is hosted by the GRCDI and led by Centre member Dr Kasim Terzić from the School of Computer Science. This in-person series for GRCDI members kicks off with a group discussion session, followed by four lectures delivered by colleagues from the School of Computer Science: Dr Kasim Terzić, Dr Ruth Hoffmann and a joint lecture by Dr Nguyen Dang and Dr Phong Le. There will be time for discussion following each lecture. The series will culminate in December with a further discussion session where participants can reflect on and discuss a question central to research on artificial intelligence: whether intelligence can be computed.