Lecture

Chemical Reactions: Transformer Architecture

Related lectures (31)

Language Models: From Theory to Computation

Explores the mathematics of language models, covering architecture design, pre-training, and fine-tuning, emphasizing the importance of pre-training and fine-tuning for various tasks.

Financial Time Series Analysis

Covers stylized facts of asset returns, summary statistics, testing for normality, Q-Q plots, and efficient market hypothesis.

Introduction to Machine Learning

Provides an overview of Machine Learning, including historical context, key tasks, and real-world applications.

Nonlinear Supervised Learning

Explores the inductive bias of different nonlinear supervised learning methods and the challenges of hyper-parameter tuning.

Improving Models of the Ventral Visual Pathway

Explores computational models of the ventral visual system, focusing on optimizing networks for real-world tasks and comparing to brain data.

Non conceptual knowledge systems

Explores the impact of Deep learning on Digital Humanities, focusing on non conceptual knowledge systems and recent advancements in AI.

Image Representation Insights

Explores the evolution of image representation, challenges in supervised learning, benefits of self-supervised learning, and recent advancements in SSL.

Supervised Learning Overview

Covers CNNs, RNNs, SVMs, and supervised learning methods, emphasizing the importance of tuning regularization and making informed decisions in machine learning.

Deep Learning: Exploring Vision and Language Transformers

Covers advanced transformer architectures in deep learning, focusing on Swin, HUBERT, and Flamingo models for multimodal applications.

Brain Intelligence: Continual Learning of Representational Models

Delves into the continual learning of representational models after deployment, highlighting the limitations of current artificial neural networks.

Transformers: Pretraining and Decoding Techniques

Covers advanced transformer concepts, focusing on pretraining and decoding techniques in NLP.

Self-Supervised Image Representation Learning

Presents BYOL, a self-supervised image representation learning method achieving state-of-the-art results without negative pairs.

Machine Learning and Modern AI: SWOT Analysis

Covers a SWOT analysis of Machine Learning and Artificial Intelligence, exploring strengths, weaknesses, opportunities, and threats in the field.

Perception: Data-Driven Approaches

Explores perception in deep learning for autonomous vehicles, covering image classification, optimization methods, and the role of representation in machine learning.

Statistical Learning: Fundamentals

Introduces the fundamentals of statistical learning, covering supervised learning, decision theory, risk minimization, and overfitting.

Reinforcement Learning Concepts

Covers key concepts in reinforcement learning, neural networks, clustering, and unsupervised learning, emphasizing their applications and challenges.

Deep Learning: Graphs and Transformers Overview

Covers deep learning concepts, focusing on graphs, transformers, and their applications in multimodal data processing.

Natural Language Processing: Understanding Transformers and Tokenization

Provides an overview of Natural Language Processing, focusing on transformers, tokenization, and self-attention mechanisms for effective language analysis and synthesis.

Molecular Synthesis Planning: Transformer Models and Atom Mapping

Explores Molecular Transformer models, atom mapping, AI synthesis planning, and the transformative role of Transformers in chemistry.

Gradient-Based Algorithms in High-Dimensional Learning

Provides insights on gradient-based algorithms, deep learning mysteries, and the challenges of non-convex problems.