Self-Attention Courses and Certifications

Generative AI Language Modeling with Transformers

This course provides you with an overview of how to use transformer-based models for natural language processing (NLP). In this course, you will learn to apply transformer-based models for text classification, focusing on the encoder component. You’ll…

• Coursera
• 8 hours 48 minutes
• On-Demand
• Free Online Course (Audit)

Transformers: Text Classification for NLP Using BERT

41 ratings at LinkedIn Learning

Learn about transformers, the go-to architecture for NLP and computer vision tasks.

• LinkedIn Learning
• On-Demand
• Free Trial Available

TensorFlow: Working with NLP

Learn about using transformers in natural language processing with TensorFlow.

• LinkedIn Learning
• On-Demand
• Free Trial Available

Open Data Science

Vision Transformer and Its Applications

Explore the breakthroughs in computer vision with Vision Transformers in this under 1-hour material by Open Data Science. Delve into model architecture, self-attention, and general-purpose model architectures.

• YouTube
• 35 minutes
• On-Demand
• Free Online Course

Yannic Kilcher

TransGAN - Two Transformers Can Make One Strong GAN - Machine Learning Research Paper Explained

Explore TransGAN, the first GAN with both generator and discriminator as transformers, in this less than 1-hour study by Yannic Kilcher. Learn about its architecture, tricks for training, and results.

• YouTube
• 30 minutes
• On-Demand
• Free Online Course

Yannic Kilcher

Nyströmformer- A Nyström-Based Algorithm for Approximating Self-Attention

Explore the Nyströmformer algorithm for approximating Self-Attention in Transformers with Yannic Kilcher. Learn about its linear memory and time requirements, and its application in Natural Language Processing.

• YouTube
• 48 minutes
• On-Demand
• Free Online Course

Edan Meyer

Recreate Google Translate - Model Training

Explore Neural Machine Translation with Edan Meyer's final video in the NMT series, covering model training, testing, and recreating Google Translate. Less than 1-hour workload.

• YouTube
• 21 minutes
• On-Demand
• Free Online Course

Andrej Karpathy

Let's Build GPT - From Scratch, in Code, Spelled Out

Learn to build a Generatively Pretrained Transformer (GPT) from scratch with Andrej Karpathy. Understand connections to ChatGPT and watch GitHub Copilot assist in coding. Requires 1-2 hours.

• YouTube
• 1 hour 56 minutes
• On-Demand
• Free Online Course

Graham Neubig

CMU Multilingual NLP - Machine Translation-Sequence-to-Sequence Models

Explore conditional language modeling, sequence-to-sequence models, and attention mechanisms with Graham Neubig's less than 1-hour material.

• YouTube
• 44 minutes
• On-Demand
• Free Online Course

Graham Neubig

Neural Nets for NLP 2020 - Document Level Models

Explore document-level language modeling, coreference, and discourse parsing in this less than 1-hour material by Graham Neubig.

• YouTube
• 52 minutes
• On-Demand
• Free Online Course

Graham Neubig

Neural Nets for NLP 2017 - Attention

Explore neural networks for NLP with a focus on attention, improvements, and specialized varieties in this 1-2 hour material by Graham Neubig.

• YouTube
• 1 hour 3 minutes
• On-Demand
• Free Online Course

Graham Neubig

Neural Nets for NLP 2021 - Document-Level Models

Explore document-level models, entity coreference, and discourse parsing in this less than 1-hour material by Graham Neubig, part of CMU's Neural Networks for NLP series.

• YouTube
• 40 minutes
• On-Demand
• Free Online Course

Prodramp

Prompt Engineering - Understanding Large Language Models with ChatGPT

Explore the technology behind large language models like ChatGPT with Prodramp's short, intensive program. Learn about transformer architecture, text embedding, and more.

• YouTube
• 36 minutes
• On-Demand
• Free Online Course

Institute for Advanced Study

Emergent Linguistic Structure in Deep Contextual Neural Word Representations - Chris Manning

Explore emergent linguistic structures in neural word representations with Stanford's Chris Manning in this under 1-hour workshop offered by the Institute for Advanced Study.

• YouTube
• 43 minutes
• On-Demand
• Free Online Course

StatQuest with Josh Starmer

Transformer Neural Networks, ChatGPT's Foundation, Clearly Explained

Understand the workings of Transformer Neural Networks, the foundation of AI innovations like ChatGPT, with StatQuest's concise, step-by-step guide. Less than 1-hour workload.

• YouTube
• 36 minutes
• On-Demand
• Free Online Course