How I Learned to Stop Worrying and Love the Transformer - Stanford CS25 Lecture
Explore the Transformer's evolution and future directions with Ashish Vaswani, co-author of "Attention is All You Need". Gain insights into motivations, developments, and promising research areas in AI and NLP.
Transformer-based Reasoning for Learning Evolutionary Chain of Events on Temporal Knowledge Graphs
Explore transformer-based reasoning for learning evolutionary event chains on temporal knowledge graphs, enhancing understanding of complex temporal relationships.
Evolution of ML Training and Serving Infrastructure at Pinterest Ads
Explore Pinterest Ads' ML infrastructure evolution, from logistic regression to transformer models, and learn key challenges and lessons in revolutionizing ad capabilities.
Finetuning a Large Language Model on a Custom Dataset
Discover parameter-efficient finetuning techniques and optimizations for large language models using custom datasets, enhancing model performance at scale.
Deep Learning on Electronic Health Records: Unlocking the Power of Clinical Data - Lecture 1
Unlock the power of EHR data using deep learning NLP. Explore frameworks for extracting clinical information, leveraging pretrained transformer models, and addressing challenges in applying language models to healthcare data.
Tensor2Tensor - TensorFlow at O’Reilly AI Conference, San Francisco '18
Explore state-of-the-art deep learning models and datasets with Tensor2Tensor, accelerating ML applications like translation, parsing, and image captioning.
Simple Training with the Transformers Trainer
Learn to train and fine-tune Transformer models using the Trainer API, covering tokenization, class balance, and practical implementation techniques.
How to Build Custom Q&A Transformer Models in Python
Learn to fine-tune pre-trained transformer models for question-answering using HuggingFace and PyTorch. Gain practical skills in NLP and unlock the power of transformers for custom Q&A applications.
Fastformer - Additive Attention Can Be All You Need
Explore Fastformer, a linear-complexity Transformer variant for efficient long text modeling. Learn about additive attention, global context interactions, and its performance compared to traditional Transformers.
Author Interview - Transformer Memory as a Differentiable Search Index
Explore a novel approach to information retrieval using a single Transformer model that encodes corpus information in its parameters, enabling direct query-to-document mapping without external indices.
Deep Learning and Transfer Learning for NLP
Explore deep learning and transfer learning for NLP with expert Dipanjan Sarkar. Gain insights on challenges, deployment, popular models, tools, and recent advances in multilingual AI and model interpretability.
Riding the Tailwind of NLP Explosion
Explore NLP's evolution, from prehistoric to modern era, and learn practical applications, challenges, and strategies for leveraging transformers and open-source tools in data science projects.
The Math Behind Attention Mechanisms
Demystify attention mechanisms in Transformer models through visuals, examples, and mathematical explanations, focusing on embeddings, similarity, and key-query-value matrices.
Mathematics as a Translation Task - The Importance of Training Distributions
Explore how mathematical problems can be framed as translation tasks, focusing on the impact of training distributions on model performance and transformer model mechanics.
Learning the Language of Chemistry
Explore chemical language through AI, focusing on molecular transformations and retrosynthesis. Gain insights into cutting-edge applications in organic synthesis.
Revealing the Unseen: Visualizing Attention in Transformer Models
Dive into the visualization techniques of attention mechanisms in Transformer models, understanding their inner workings and practical applications through expert insights.
Robotics Policy Optimization for Multi-Agent Drone Swarms Using Game Theory
Explore advanced reinforcement learning applications in optimizing taxi fleets and drone swarms, focusing on multi-agent systems and environmental interaction strategies.
Parameter-Efficient Fine-Tuning with LoRA - Optimizing LLMs for Local GPU Training
Master PEFT LoRA techniques to efficiently fine-tune large language models on local GPUs through low-rank adaptation, reducing memory requirements while maintaining model performance.
Drinking From The Firehose of Science: Developments in Semantic Scholar and Scientific Literature Access
Explore recent developments in Semantic Scholar and learn how to leverage its APIs for scientific literature analysis. Discuss strategies to increase diversity in scientific participation.
From NLP to NLU: Why We Need Varied, Comprehensive, and Stratified Knowledge - Neuro-Symbolic AI
Explore the importance of knowledge in AI systems for improved language understanding, addressing challenges in generative AI, and enhancing neuro-symbolic approaches for safer, more explainable AI.
Deep Learning for ESG: Advances and Limitations
Explore recent NLP advances in ESG analysis, including transformer models and transfer learning. Understand the advantages and limitations of current technology in ESG domain.