Explained by the Community | 200 CHF Cash Prize X 5

Learning to Smell
#1

Announcing Community Contribution Prize! :tada:

Create an explainer on the Learning to Smell Challenge This explainer must be in the form of a video or an article - and must be accompanied by a notebook. It should be succinct, and simple. The deadline for submitting it closes 4 days before Round 1 of the competition ends.

Post a link to your explainer as a reply to this post.

:trophy: A cash prize of 200 CHF to Top 5 Community Contributors each!

:date: New Deadline: 23rd October, 2020, 12:00 UTC

Also, check out Community contributions for other challenges to get inspired!

The competition is simple:

  1. There are no constraints on how you wish to present your ideas. You can be as creative as you want!
  2. You must post your explainers on the challenge forum with the tag ‘explainer,’ and must also provide a link for the same on any of your social media handles, from any platform.
  3. You can make multiple submissions, but you’re only eligible for the prize once.
  4. All the explainers should be supported by atleast a working Google Colab notebook.
  5. The prizes will be awarded as per the discretion of the organizers and the popularity of the post in the community (based on upvotes).

Looking forward to see what you come up with!

4 Likes
🏆📝 Learning to Smell Community Prize Winners (Round 1)
📅 Round-1 Deadline Extension
#2
#3

I’d really appreciate your feedback!

Made a simple colab notebook explainer for aicrowd Learning to Smell Challenge:https://t.co/XOsSRGAyhv

September 30, 2020
3 Likes
#4

Hi everyone,

I wrote a tutorial on how to build a baseline logistic regression model, hope you find it useful. Some of the topics I covered are:

  • Basics of the SMILES format
  • Data exploration - frequency of the odors
  • Converting the data into a format that can be used as input to the model
  • Building / training a logistic regression model with Keras
  • Making and formatting predictions for submission
  • Evaluating the model on the training set with Jaccard Index / Tanimoto Similarity Score

Here is the Colab notebook:
https://colab.research.google.com/drive/143hNxXLAje5_HvbEPnt4N6l7ZHcv9yWY?usp=sharing

4 Likes
#5

Hi everyone,

I wrote a Google Colab tutorial/explainer on how to use vectors created with the SMILESVec package to train a fully-connected neural network using Tensorflow Keras on the learning to smell dataset:

https://colab.research.google.com/drive/1cePlnWwWOsYxwqs8NWebVHFwRr624tNc?usp=sharing

Let me know if you have any suggestions or questions, always happy to help out!

Cheers,
Cas

4 Likes
#6

hey there everyone I tried this with fastai (amazing library) which gives state of art out of the box
let’s have look and please let know for further improvement

there are lot other things like discrimative learning rate and learning rate finder can be use for further improvment

https://colab.research.google.com/drive/1g5I-N0KZnP7yGJyAyFdvDonOzrg-aVLx?usp=sharing

3 Likes
#8

Dear Community,
My submission is also a very basic one, despite that it gives a high score on the current leaderboard. I hope that I’ll manage to find some spare time to write something more interesting in the upcoming rounds, that’s why I’ve decided to publish it.

I wrote a Medium post with a short explanation and some thoughts about what to do next.
Google Colab can be found here, and GitHub repository with the full source code is there.

9 Likes