Interested in joining a learning cohort for part 1 in early January?

I’m interested in starting part 1 in early January. I think it would be great to have a little learning cohort to help with accountability and to have people to bounce ideas off of and work through problems with.

If you’re serious and interested in starting in the first or second week in January and plan to put ~10 hours/week into completing the course, reply here!

1 Like

I am interested ! Shall be starting as soon as it is released.

I’m in. I’m looking forward to getting started!

I already started now. There isn’t people here around to answer questions anymore. What a pity!

@elpa Sounds good!

@naman-bhalla I’m not sure what you mean…it’s all already released, no?

@damien How far are you? If you wanted to join our cohort you could wait for us to catch up…

I’m open to other ideas but what I was thinking (depending on how many people are interested) would be to have a once or twice weekly chat about the progress we’re making the problems we run into. Of course, we can also make a group chat or something where we could stay in touch outside of those meeting times.

I started lesson 1. Some content of video 2,3 I already knew. So basically, I start from lecture 4. I don’t have much of time to study so we will catch up each other soon. Be aware that some content is already dated. So it will be really annoying if you get any error when try to reproduce the result e.g. two results from 2 platforms with the same code and weights.

ineterested

I’m interested too - to start on january 15 -maybe a bit earlier for all the setup.

I’d also prefer to start with the new learning materials expected in 2018, based on Pytorch (currently installing it to do Pytorch basic tutorials)

Since I’m not confident with the AWS settings, I’m trying to set up the GCP solution (any help most welcome)

1 Like

I am also waiting for the new material, meanwhile, I am checking out Rachel’s linear algebra course.

For GCP setup for Part1 with old materials(Not sure when will the Pytorch version be released):

@nok : thanks

I think you still can start to learn about the concept. It will not change with new material.

1 Like

I’m in - am starting part 1 now.

The new course material coming would be “Part 3” i suppose.

even if the previously posted material re- Part 1 is dated, it wont hurt to learn that. The main concepts (types of layers, Python, loss, activation, etc) of DL is going to remain the same I guess.

I am finished with Lesson 2 part 1, now starting with lesson 3.

With 10 hours a week, for someone with no background in DL before is an rather optimistic estimate. I am not just rushing through the videos but rather trying to finish the assignments with minimum requirements at least and it is taking me roughly 20-25 for that so far. With Lesson 1 it took me almost a month because i also started setting up my own System. (For the record I am a developer with no experience with Python, Linux, DL so have to learn all of these at the same time).

but the good thing is, there is no class with which one has to keep the pace, rather the material is there, one can learn at one’s own pace.

1 Like

I’m in, have already completed first three weeks but could wait for cohort. I also think its ideal to start fresh with the Pytorch version of Part 1 or switch when it is available. What do you think?

Count me in! I’m currently on Lesson 3, but happy to work with the cohort in Jan.

By the way – where’s the announcement of the new Pytorch version of Part 1? I must’ve missed it.

Hey, this sound great, count me in.
By the way I am still struggling to run jupyter notebook on GCP and I’ll start as soon as I figure it out.

This sound awesome, I’m in. I suggest creating a new Slack groups for January cohort for betting better communicating, especially for newcomers :wink:

@afrocart you can find the Pytorch choice in this annoucement, and also several discussions in the forum http://www.fast.ai/2017/09/08/introducing-pytorch-for-fastai/

@nok : thanks for sharing the link to GCP setup. Has anyone been able to customize this set up procedure with Python 3+ which is a requirement for Pytorch (from my understanding) ? I was able to install Pytorch+Anaconda+Jupyter+Cuda support on local to use with my desktop GPU, but i’m not at ease with cloud deployment. Oops just found this install script :https://gist.github.com/motiur/2e0cd3d35bc1c42b6e5d6046b65be6f4 , just need how to find out how to deploy that on GCP

I browsed the forum a bit to see the discussions on Pytorch and the upcoming course material. Here is one thread

one correction to my above post: It seems the upcoming course will be a Pytorch version of existing Part 1 (or 2?) .

There is also Pytorch version of Part1 available by a fellow student:

So this brings to the question :

  1. should i wait to start till next material is released ?
  2. Start learning pytorch from the already posted Part1 notebooks with Pytorch
  3. learn via the “old” keras notebooks and when the new material is available switch to that.

I am still sticking with option 3 to continue making a foundation of concepts. So that switching to pytorch will be easier (hopefully). Switching now to Pytorch seems a bit challenge to me when there are no video lectures available. (if anyone learning DL first time with Pytorch has experience plz share it).

Interested!