Intro to Dense Vectors for NLP and Vision
Offered By: James Briggs via YouTube
Course Description
Overview
Explore the evolution and importance of dense vector representations in Natural Language Processing (NLP) and computer vision. Learn about the groundbreaking word2vec model and its impact on the field, then dive into modern approaches like Sentence Transformers, Dense Passage Retrieval (DPR), and Vision Transformers. Discover practical applications through Python implementations, including question-answering systems and OpenAI's CLIP model for image-text understanding. Gain insights into why dense vectors are crucial for advancing NLP and vision technologies, and prepare for future developments in these rapidly evolving fields.
Syllabus
Intro
Why Dense Vectors?
Word2vec and Representing Meaning
Sentence Transformers
Sentence Transformers in Python
Question-Answering
DPR in Python
Vision Transformers
OpenAI's CLIP in Python
Review and What's Next
Taught by
James Briggs
Related Courses
Interactive Word Embeddings using Word2Vec and PlotlyCoursera Project Network via Coursera Машинное обучение на больших данных
Higher School of Economics via Coursera Generating discrete sequences: language and music
Ural Federal University via edX Explore Deep Learning for Natural Language Processing
Salesforce via Trailhead Advanced NLP with Python for Machine Learning
LinkedIn Learning