Machine Translation
Explore AI-powered language translation, from statistical models to neural networks. Learn about RNNs, LSTMs, and sequence-to-sequence models, with a practical English-to-French translation example.
YouTube-VOS: Sequence-to-Sequence Video Object Segmentation
Learn sequence-to-sequence video object segmentation techniques, exploring datasets, algorithms, and metrics. Gain insights into YouTube-VOS implementation and experimental results on various benchmarks.
Iterated Models: Expressive Power, Learning, and Chain of Thought
Explore sequence-to-sequence models, focusing on transformers, their computational power, and learning complexities. Gain insights into iterated functions and chain of thought.
Introduction to Transformers
Dive into the fundamentals of Transformers, exploring their architecture and applications in large language models with expert insights from Columbia University.
How Do Transformers Work? - A Deep Dive into Neural Network Architecture
Dive into the fundamental mechanics and architecture of transformer models, exploring their key components and operational principles through expert insights from MIT's research.
Fine-tune T5 Language Model for Text Summarization on Google Colab
Master fine-tuning techniques for T5 language models using HuggingFace's latest code, focusing on text summarization tasks with hands-on implementation in Google Colab's free GPU environment.
Attention Mechanism and Self-Attention in Deep Learning - Lecture 9
Dive into attention mechanisms and self-attention concepts in deep learning, exploring their revolutionary impact on NLP and discovering practical applications in sequence models.
Introduction to Machine Translation with Sequence-to-Sequence Models
Master sequence-to-sequence modeling fundamentals and applications in machine translation, focusing on neural network architectures and practical implementation techniques.
Finetuning a Sequence-to-Sequence Model with RLHF
Master sequence-to-sequence model finetuning techniques and reinforcement learning from human feedback (RLHF) through hands-on demonstrations and practical implementations.
Understanding Names with Neural Networks - Session 2
Explore neural network-based approaches for cross-language name matching, focusing on English/Japanese pairs and comparing traditional methods with advanced deep learning techniques.
Understanding Names with Neural Networks - Session 1
Explore neural network approaches for cross-language name matching, focusing on English/Japanese. Learn about seq2seq models, LSTMs, and CNNs for improved accuracy in transliteration and scoring.
Pytorch Transformers for Machine Translation
Build a Seq2Seq Transformer model in PyTorch for German-to-English translation using the Multi30k dataset. Learn data preprocessing, model architecture, training setup, and evaluation with BLEU score.
Pytorch Seq2Seq Tutorial for Machine Translation
Comprehensive tutorial on building a Seq2Seq model for German-English machine translation, covering implementation, training, and evaluation using PyTorch and the Multi30k dataset.
CMU Multilingual NLP - Machine Translation-Sequence-to-Sequence Models
Explore conditional language modeling, sequence-to-sequence models, generation methods, attention mechanisms, and transformers in multilingual natural language processing.
CMU Neural Nets for NLP 2020 - Multitask and Multilingual Learning
Explore multitask and multilingual learning in NLP, covering methods, objectives, and challenges. Gain insights into cross-lingual transfer, data balancing, and zero-shot approaches.
Spinning Language Models: Risks of Propaganda-as-a-Service and Countermeasures
Explore risks and countermeasures of using language models for propaganda, including classification vs sequence-to-sequence models, spin techniques, and defense strategies.
Deep Learning for Symbolic Mathematics
Explore neural networks solving complex mathematical problems like symbolic integration and differential equations, outperforming traditional Computer Algebra Systems.
Deep Learning for Natural Language Processing
Explore NLP architectures, transformers, language models, and advanced techniques for text generation and embedding learning in this comprehensive deep learning lecture.
DALL-E Mini - Generate Images From a Text Prompt
Learn about DALL·E mini, a smaller version of OpenAI's DALL·E that generates images from text prompts. Explore its architecture, training process, and capabilities in this comprehensive overview.
Beyond Standard Deep Learning Models for Time Series and Sequences
Explore advanced techniques for temporal data analysis, including confident predictions and adaptive computational time models for improved sequence-to-sequence processing.
Streaming Sequence Transduction through Dynamic Compression
Explore efficient sequence-to-sequence transduction with STAR, a novel Transformer-based model for streaming ASR and simultaneous speech-to-text tasks.