Lesson 4 In-Class Discussion


(Maureen Metzger) #183

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


(Karthik Ramesh) #184

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


(Rajat) #185

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


(Pramod) #186

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.


(Kevin Bird) #187

Neural Net book/article Editor maybe?


(Rafael Valdivia) #188

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


(Aditya) #189

language model?

Can someone provide an intuitive explanation(brief)

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


(anamariapopescug) #190

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


(Rafael Valdivia) #191

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


(Ben Eacrett) #193

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


(helena s) #194

hopefully, fake news classification too


#195

What is the difference between this and word2vec from Google


(Pranjal Yadav) #196

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

The first half of this post talks about it.


(Pramod) #197

Only RNNs take IMDB reviews so seriously!!


(yinterian) #198

They way you learn the embeddings is different.


(Rajat) #199

Is vocal similar to bag of words?


(Charles C. Lee) #200

what about removing stopwords?


(Setu) #201

why would we not use word vectors?


(Pete Condon) #202

Stopwords are important in this kind of problem :slight_smile:


(Charles C. Lee) #203

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