CORRECTION: at 1:33, that should be "20,000-element vector" . Timestamps 00:00:00 Word Vectors 00:00:37 One-Hot Encoding and its shortcomings 00:02:07 What embeddings are and why they're useful 00:05:12 Similar words share similar contexts 00:06:15 Word2Vec, a way to automatically create word embeddings 00:08:08 Skip-Gram With Negative Sampling (SGNS) 00:17:11 Three ways to use word vectors in models 00:18:48 DEMO: Training and using word vectors 00:41:29 The weaknesses of static word embeddings
So I attend a really, REALLY prestigious university in the US and I took a course on Neural Networks this last term--this video series has higher lecture quality than that. You are very good at teaching these concepts
I have watched 5 videos on this subject in the last 2 days, and browsed dozens. This one is OUTSTANDING!!! By far the best i have seen. Wow! I will do the whole NLP course. Very grateful for Huge effort it took
In SGNS, when you are talking about matrices of context and target embeddings (10000 * 300), what do these matrices have/contain before the training has started (collection of one hot encodings or arbitrary numbers)? At 17:00, I also did not understand how only taking the target word embeddings would be sufficient to capture similarity between words.
I saw openai also provide embedding tool. It seems that this make easier than the old library such as NLTK,spacy, making them outdated? It make these concepts as a black box for us. We do not need to know in detail if only to use it.
Absolutely. LLM APIs (even open source ones), hide all the details and make it easy for anyone to build NLP applications. We explore these APIs in part two and see how things like sentiment analysis can be done with a single line now.
CORRECTION: at 1:33, that should be "20,000-element vector" .
Timestamps
00:00:00 Word Vectors
00:00:37 One-Hot Encoding and its shortcomings
00:02:07 What embeddings are and why they're useful
00:05:12 Similar words share similar contexts
00:06:15 Word2Vec, a way to automatically create word embeddings
00:08:08 Skip-Gram With Negative Sampling (SGNS)
00:17:11 Three ways to use word vectors in models
00:18:48 DEMO: Training and using word vectors
00:41:29 The weaknesses of static word embeddings
So I attend a really, REALLY prestigious university in the US and I took a course on Neural Networks this last term--this video series has higher lecture quality than that. You are very good at teaching these concepts
Thank you!
A lot of UA-camrs teach better than a lot of “professors”.
I have watched 5 videos on this subject in the last 2 days, and browsed dozens. This one is OUTSTANDING!!! By far the best i have seen. Wow!
I will do the whole NLP course. Very grateful for Huge effort it took
Thank you! I hope you get a lot out of it.
You are very good at teaching
Great work 👍
In SGNS, when you are talking about matrices of context and target embeddings (10000 * 300), what do these matrices have/contain before the training has started (collection of one hot encodings or arbitrary numbers)? At 17:00, I also did not understand how only taking the target word embeddings would be sufficient to capture similarity between words.
I saw openai also provide embedding tool. It seems that this make easier than the old library such as NLTK,spacy, making them outdated? It make these concepts as a black box for us. We do not need to know in detail if only to use it.
Absolutely. LLM APIs (even open source ones), hide all the details and make it easy for anyone to build NLP applications. We explore these APIs in part two and see how things like sentiment analysis can be done with a single line now.
@@futuremojo Great, your lectures uncovered these concepts hidden in the Blackbox.
@@futuremojo I also look forward to these lectures. Thank your lectures to know so many hidden concepts.
Are you planning to do courses on other machine learning topics, such as computer vision?
I probably won't build another course. This one took a year. I would consider more frequent, short-form videos though. What would you find useful?
@@futuremojo Perhaps some material on diffusion models
@@futuremojo yes definitely
Thank you !
Awesome !