Lesson 5 In-Class Discussion

Part 1 (2018)
85

Ah so basically we took the user-item vectors, concatenate them with other variables and put them through neural network.

1 Like
86

“How many times are deprecating comments made toward the main character”

Personal preference: High
Average user preference: Neutral

87

People have asked this question earlier and have NN-ed Movie recommendations, but matrix factorization techniques are still used in production at places such as Netflix, Amazon and MSFT.

1 Like
88

Jeremy and his excel skills are exceptional :smiley:

6 Likes
89

Thanks!

90

Wonder If he can teach us that also…

1 Like
91

Are there any good collab filtering datasets that we can work on/explore?

92

Right. I wonder how nns compare to the classical matrix factorization methods?

1 Like
93

netflix dataset

2 Likes
94

https://www.netflixprize.com/

3 Likes
95

The Amazon review dataset is an interesting one. Could even do some NLP on written reviews to determine sentiment to add in as s feature.

https://snap.stanford.edu/data/web-Amazon.html

3 Likes
96

please also check movieLens, LastFM and jester.

PS : Jester is a joke recommendation dataset.

1 Like
97

In the case of NN collaborative filtering, how would you do the exploration phase ?

98

Movies dataset https://www.kaggle.com/rounakbanik/the-movies-dataset

3 Likes
99

That’s a good question. I’d probably spend a little time getting familiar with the data itself (missing values, what the variables are, etc.), then try to wrangle it into a format very similar to today’s lecture. Then I’d try to follow along with Jeremy’s example (I’d use the fastai abstractions!)

How would you approach it?

100

I prefer these ones(short and concise)

9 Likes
101

Regarding Jacobian and Hessian: I like how they are described in the Deep Learning book. See section 4.3.1 (page 84) here: http://www.deeplearningbook.org/contents/numerical.html

8 Likes
102

Some good resources on backpropagation:

Backpropagation as a chain rule by Chris Olah: http://colah.github.io/posts/2015-08-Backprop/
Another explanation about the chain rule from Andrej Karpathy: http://cs231n.github.io/optimization-2/
Why you should understand backpropagation: https://medium.com/@karpathy/yes-you-should-understand-backprop-e2f06eab496b

14 Likes
103

lr is provided by us. can we control da in de/da ? or does pytorch figure that out ?

104

Can someone please share intuitive Jacobian and Hessian matrix explanation with how they are calculated. Thanks