YSC Summer School 2021 Materials

These are all the materials used in Yachay Scientific Computing Summer School 2021. For more details, you can visite the oficial webpage: https://www.yachay-scg.com/summer-school

Opening Slides

Journal Club

Article	Link	Slides
Attention Is All You Need
A Stochastic Phylogenetic Algorithm for Mitochondrial DNA Analysis

Tutorial Notebooks

Title	Date	Link	Slides
Transfer Learning in Tensorflow	Day 1 - September 20
Introduction to Reinforcement Learning with Python	Day 2 - September 21		--
Introduction to Quantum Computing with Qiskit	Day 3 - September 22
Bayesian Neural Network	Day 4 - September 23		--
Self-Organizing Maps to process COVID-19 databases	Day 5 - September 24

Lectures

Lecture	Slides
Day 1 - Development of Various Industrial Technologies Based on Artificial Intelligence
Day 1 - Time series encoding in Neural Networks	--
Day 2 - Reinforcement Learning: From a Mathematical Concept to a Powerful Technological Tool
Day 2 - Deep Learning for Near Real Time Deforestation Detection	--
Day 3 - Predicting Choice in Matrix Games Using Transfer Learning	--
Day 3 - Machine Learning with Bio-Ontologies
Day 4 - Smart System in Health Care
Day 4 - The Last Wave of NLP
Day 5 - Bioinformatics for SARS-CoV-2 genomics, the pandemic COVID-19 virus	TBD
Day 5 - Human Activity Detection for Emergency Response in Smart Spaces using Multiple Sensors

Challenge Resources

Source	Link
Pytorch Template
Tensorflow Template
Modified Dataset

Challenge Guideline

In this competition, you are challenged to build a deep learning model that identifies different types of natural scenes in a dataset of images, where the images have been noisy (between 15-25% of the image was randomly covered by a black rectangle).

The dataset counts with 6 natural scene categories: buildings, forest, glacier, mountain , sea , street.

The dataset was dividided in train: 9300 images, val: 3000 images, test: 4734

Rules

• This is an individual competition, only for Scientific Computing Summer School 2021 participants.

• You will work with the dataset available at:

  dataset_sc_2021.zip

• Your task is to propose a model to obtain best classification results using the provided test subset (a part of the data_scg_2021.zip).

• The participants of this challenge will be required to send the code of the created solution (in a ZIP file) for further check.

• The results will be evaluated by the organizers and three best entries will be awarded.

• The winners of the competition will be asked to send a short video (1-5 minutes) or PDF slides with a presentation of their solution. The film or slides will be placed on the SCG 2021 website, therefore matters relating to the privacy of submitters must be properly considered when preparing the video).

Evaluation

Submissions will be evaluated on a weighted F1 score using a scikit-learn function. The submission website will be announced on Slack.

F1 score function

parameters:

• average='weighted'
• other parameters - default.

The proposal presentation will hold 3-5min and is about your progress, proposal, or just ideas about dealing with the problem.

Also, we will require you to submit two files with your results. The submission website will be announced on Slack.

1. We require a .csv file where for each id in the test set, you must predict a type of natural scene (or label). The file should contain a header and have the following format:

   id,label
   22010,B
   22006,F
   22013,G
   24025,M
   8046,S
   803,ST

   where

   • B indicates buildings
   • F indicates forest
   • G indicates glacier
   • M indicates mountain
   • S indicates sea
   • ST indicate street

   The submission file should be named:

   sample_submission_firstname_lastname.csv

2. We require you to send the code of the created solution (in a ZIP file) for further check. Use the following format for the name sample_submission_firstname_lastname.zip

Schedule

Activity	Date
Start of the competition	September 10, 2021
Proposal Presentation	September 24, 2021
End of time for sending results	October 1, 2021
Announcement of results-> Awards	October 4, 2021

Information about data set

The dataset used in this challenge is the "Intel Image Classification" dataset provided by Puneet Bansal.

Source: https://www.kaggle.com/techsash/waste-classification-data

Licence: CC BY-SA 4.0

The dataset has been processed for the needs of this challenge