The CSIRO Conference on Computational and Data Intensive Science

Introduction to machine learning for science

Machine Learning Workshop Description:

CSIRO is holding a 2-days multidisciplinary workshop on Machine Learning that will integrate the most fundamental theory, cutting-edge technologies and its real-world implementations in this field.

The Machine Learning workshop aims to:

  1. Bring together researchers from different fields to discuss Machine Learning related science and application challenges
  2. Exchange knowledge and opinion between researchers working in Machine Learning algorithms, infrastructures, and its applied research background
  3. Initiate and enhance collaborative partnerships between CSIRO and other experts in the field of Machine Learning

Amongst the invited trainers and speakers are scientific and technical leaders in this field from CSIRO.

Webpages:

C3DIS: https://wp.csiro.au/c3dis/

Machine Learning Workshop: http://wp.csiro.au/c3dis/workshops/advanced-machine-learning-for-science/

Key Points to Address:

  1. Basic Introduction and Overview to Machine Learning (Hands-on/Seminar)
  2. Studies Cases on Different Scientific Topics (Seminar/Presentation)
  3. Hands on Lab Tutorial (Advanced Techniques of Machine Learning)
    1. Spark + Machine Learning (Big Data)
    2. Tensorflow + Deep Learning (NVIDIA Digits, Keras and Tensorflow)
  4. Panel discussion & QA
  5. One-on-one discussion (10mins each audience) with ML experts about “How to better utilize ML in your project”

Important Notice for Day 1 Attendees

Please read the information on this this link about how to prepare before the training: https://github.com/piotrszul/spark-tutorial

Agenda

Time Session
09:00 am – 10:30 am Hands-on Lab for Basic Intro and Overview to Machine Learning

Christopher Watkins

·         sklearn/tensorflow

·         Un-/Supervised ML

·         Classification/Regression

·         Dimension Reduce

·         Anomaly Detection

·         Recommendation System

·         Q&A

10:30 am – 11:00 am Morning Tea and Networking
11:00 am – 12:00 am Hands-on Lab for Introduction to Working with Structured Data with Apache Spark in Python

Piotr Szul

·         Introduction to data frames

·         Analyzing data with data frames (grouping, aggregating etc.).

·         Working with structured data formats (CSV, JSON, parquet)

12:00 pm – 13:30 pm Lunch and Networking
13:30 pm – 15:00 pm Hands-on Lab for Machine learning with Apache Spark in Python

Piotr Szul

·         Training simple ML regression and classification models

·         Model validation and evaluation

·         Basic feature engineering

·         Machine learning pipelines

·         A case study: application to a Kaggle competition

15:00 pm – 15:30 pm Afternoon tea and networking
15:30 pm – 16:30 pm Hands-on Lab for Introduction to SparkR and Running Apache Spark at Scale

Piotr Szul

·         Introduction to Spark in R

·         Running spark on the Cloud and a cluster

16:30 pm – 17:00 pm Q&A

 

What you need to bring for Hands-on Labs:

All audience must bring their own laptop:

  • No tablets
  • Requires dual-core processor with 4GB of RAM and Wi-Fi enabled
  • Power cable

Date and time

Monday 17th July, 2017.

Location

Room: Clarendon A, level 5.
Melbourne Convention and Exhibition Centre
1 Convention Place, Melbourne, Victoria

Contact information

Baichuan Sun: Baichuan.Sun@data61.csiro.au


Comments are closed.

Attendance

The C3DIS 2017 will bring together researchers with computational and data science specialists from CSIRO, publicly funded research organisations and other invited institutions and organisations. This will enable attendees to share their science outcomes and learnings, and build a community of practice around Computational and Data Intensive science.

Cost:
Free for CSIRO staff and invited participants