Lesson 4 In-Class Discussion

@anamariapopescug, yes, and so are academics LOL :slight_smile:

1 Like

Is this a word model or a character model - so if jeremy gave it an incomplete word like toward would it complete that

1 Like

This may help
https://hackernoon.com/building-brundage-bot-10252facf3d1

6 Likes

and while we are at it, another neural network will proof-read it and another shall peer-review it.

Okay last one, the List of Sequentially Torched Matrices (LSTM) committee shall decide whether to accept it or reject it.

4 Likes

Neural Net book/article Editor maybe?

2 Likes

because of cost of computing can be improved if we learn the basics first

like the way we showed smaller images first…then bigger in CV

language model?

Can someone provide an intuitive explanation(brief)

My best guess is its equivalent to CNN’s Architectures?

it’s a probability distribution over sequences of words. you’re basically learning how likely/unlikely sequences of words are from training data. So you’ll learn that “convolutional neural network” has high prob but “convolutional neural algorithm” is an unlikely sequence

3 Likes

words are pixels, their relations have meanings like pixels express images.
You model those relationships to then be able to classify/predict words in the same space/domain

1 Like

This blog intro’s it well - by one of the thought leaders:
http://karpathy.github.io/2015/05/21/rnn-effectiveness/

4 Likes

hopefully, fake news classification too

4 Likes

What is the difference between this and word2vec from Google

If anyone needs understanding around “Word Embeddings” without diving deeper into RNNs

The first half of this post talks about it.

2 Likes

Only RNNs take IMDB reviews so seriously!!

1 Like

They way you learn the embeddings is different.

3 Likes

Is vocal similar to bag of words?

what about removing stopwords?

1 Like

why would we not use word vectors?

Stopwords are important in this kind of problem :slight_smile:

2 Likes

Yeah can’t say that the is all that important in classification. :wink: