Mediaspace scheduled maintenance: Aug 25, 2026 07:00 - 12:00 AM. During this time, videos will be temporarily unavailable. Check status updates.

Lecture

Foundations of Deep Learning: Transformer Architecture Overview

Related lectures (46)

Visual Intelligence: Machines and Minds Log in to Mediaspace to watch this video

Covers visual intelligence, feedback networks, taxonomy-based prediction, and recurrent neural networks for image classification.

Machine Learning Accelerators: Types and Efficiency Log in to Mediaspace to watch this video

Explores machine learning workloads, DNN layers, systolic arrays, and the efficiency of specialized accelerators like TPUs.

Learning-aided Program Reasoning Log in to Mediaspace to watch this video

Explores bug-finding, verification, and the use of learning-aided approaches in program reasoning, showcasing examples like the Heartbleed bug and differential Bayesian reasoning.

Matlab 2: Vectorisation and Functions Log in to Mediaspace to watch this video

Covers vectorisation, functions, and flow control in Matlab, emphasizing the importance of avoiding global variables and providing examples of simple plots and debugging techniques.

Coreference Resolution Log in to Mediaspace to watch this video

Covers coreference resolution, models, applications, challenges, and advancements in natural language processing.

Machine Learned Interatomic Potentials Log in to Mediaspace to watch this video

Delves into machine learned interatomic potentials, showcasing their accuracy and cost-effectiveness in predicting chemical properties.