Lecture
Machine Translation: Sequence-to-Sequence and Attention
Related lectures (54)
Neural Networks for NLP
Covers modern Neural Network approaches to NLP, focusing on word embeddings, Neural Networks for NLP tasks, and future Transfer Learning techniques.
Deep Learning for Autonomous Vehicles: Learning
Explores learning in deep learning for autonomous vehicles, covering predictive models, RNN, ImageNet, and transfer learning.
Air Pollution Analysis
Explores air pollution analysis using wind data, probability distributions, and trajectory models for air quality assessment.
Transformer Architecture: The X Gomega
Delves into the Transformer architecture, self-attention, and training strategies for machine translation and image recognition.
Generalization Error
Explores generalization error in machine learning, focusing on data distribution and hypothesis impact.
Document Analysis: Topic Modeling
Explores document analysis, topic modeling, and generative models for data generation in machine learning.
Natural Language Generation
Explores natural language generation, focusing on building systems that produce coherent text for human consumption using various decoding methods and evaluation metrics.
Bernoulli convolutions: The dimension of Bernoulli convolutions
Explores the dimension of Bernoulli convolutions, discussing fair tosses and polynomial roots.
From Attention to Transformers
Explores the evolution from attention mechanisms to transformers in modern NLP, emphasizing the significance of self-attention and cross-attention.
Deep Visual Recognition: Interpretability
Explores deep visual recognition, interpretability, CNN architectures, visual dictionaries, and attention mechanisms.