$867.34 – $1,444.84

Machine Learning: A Primer for Aspiring Data Scientists [5-6 November -- Br...

Event Information

Share this event

Date and Time

Location

Location

Level 7

757 Ann St Fortitude Valley QLD 4006

Brisbane, QN 4006

Australia

View Map

Event description

Description

For up-to-date Information, testimonials, updated session's information, visit:

http://www.datasmelly.com/trainingAppliedML.html

Outline

This course provides you with a complete introduction to Machine Learning. It is one of the most comprehensive two days course in Machine Learning.

The goal of this offering is to bring "Machine Learning methods and techniques" out of research Labs and share its ownership with other parties who can greatly benefit from it:

•We believe that a lot of gap exists between research world (academia) and industry. A goal of this course is to close that gap.

•Secondly, we believe that a careful designed machine learning component can greatly differentiate an application/product from its competitors. This, however, requires under-the-hood understanding of machine learning. The goal of this course is to provide an excellent foundation in machine learning, so that one can think in terms of machine learning concepts and can easily incorporate analytical algorithms in their applications.

The course is combination of both theory and practice. It not only provides a good overview of main machine learning concepts but also provide guidelines to apply these concepts to solve domain specific real world problem.

The course is update-to-date with the latest research. For example, it covers recent topics in Machine Learning such as Factorization Machines (very popular in online advertisement placement, large-scale learning, etc.), Feature Engineering (secret sauce behind all practical and effective algorithms), Deep Learning, etc.

Other main topics include, fundamental problems such as classification, regression, prediction, anomaly detection, model selection, clustering, dimensionality reduction, recommender systems, etc.

Duration

2 days (10 + 10 hours)

Training Breakdown

(*) Note the unit breakdown in the following is likely to change, but it provides a general overview of the topics that this training will cover.

Module

Session 1 -- Introduction

1A - Machine learning, Artificial Intelligence, Statistics, Data Mining and More

1B- Machine learning applications in our daily lives

1C - Introduction to Data Science and Big Data

1D - Ingredients of Machine Learning -- Data, Model and Process

  • Statistics 101
  • Basic Elements of Statistics
  • Random Variables, Probability Density/Mass Function, Expectations
  • Rules of Probability

1E - Training your first practical model

Session 2 -- Data Wrangling Lab

2A - Python 101

2B - Introduction to Data Structures in Python

2C - Storing and Manipulating Data

Session 3 -- Supervised Machine Learning

3A - Regression

  1. Linear Regression, Polynomial Regression

3B - Classification

  1. Logistic Regression
  2. Generative vs. Discriminative Learning
  3. LDA/QDA
  4. Naive Bayes, Decision Trees
  5. Nearest Neighbour Methods

3C - Prediction

  1. Moving Averages
  2. ARIMA

3D - Rank Learning

3E - Structure Learning

  1. Hidden Markov Models
  2. Conditional Random Fields

Session 4 -- Machine Learning Lab I

4A - Introduction to Sci-kit Library

4B - Classification/Regression/Prediction/Ranking examples

Session 5 -- Model Selection

5A - Bias and Variance Analysis

5B - Achieving Low-variance

  1. Regularization
  2. Feature Selection

5C - Achieving Low-bias

  1. Feature Construction
  2. Kernel and Kernel trick

5D - Feature Engineering

  1. Generalized Linear Models
  2. Factorization Machines
  3. Deep Learning

5E - Evaluating and Comparing Models

  1. Cross-validation
  2. Lift Charts, ROC, RPC, other metrics
  3. Statistical Tests, Null-Hypothesis, Friedman Statistics, etc.

Session 6 -- Un-Supervised Machine Learning

6A - Clustering

  1. K-means, DB-Scan, Hierarchical

6B - Density Estimation

6C - Bayesian Networks

6D - EM Algorithm for Clustering and Gaussian Mixture Models

6E - Curse of Dimensionality

6F - Similarity Measurements

  1. Exact vs. Approximate Similarity

6G - Local Sensitive Hashing (LSH)

6H - Data Pre-processing

  1. Data Standardization
  2. Data Munging
  3. Feature Hashing

6I - Representation Learning

  1. word2vec
  2. Graph Embedding

6I - Dimensionality Reduction

  1. Eigen-Value Decomposition
  2. Principal Component Analysis (PCA)
  3. Independent Componet Analysis (ICA)

6J - Overview of Anomaly Detection

6K - Association Rules and Discovery

  1. Apriori Algorithm

Session 7 -- Machine Learning Lab II

7A - Building a Machine Learning evaluation framework

7B - Clustering and visualizing Examples

Session 8 -- Recommender Systems

8A - Data Structure of Recommender Systems

8B - Content-based Recommendations

  1. Collaborative Filtering
  2. Memory-based
  3. Model-based
  4. Others

8C - Addressing cold-start problems

8D - Content-based Recommendations

8E - Collaborative Filtering Revisited

  1. Matrix Factorization (SVD and others)

8F - Advertising on the Web

  1. Ad Placement

Session 9 -- Advanced Machine Learning

9A - Ensemble Learners

  1. Boosting, Bagging, Stacking
  2. Random Forests and Gradient Boosting

9B - Deep Learning

  1. Artificial Neural Networks
  2. Auto-Encoders and Boltzmann Machines
  3. Deep Belief Networks
  4. Convolutional Neural Networks
  5. Recurrent Neural Networks

9C - Text Mining

  1. Name Entity Recognition
  2. Topic Models

9D - Causality

  1. Randomization
  2. A/B/n Testing
  3. Lessons learned from large-scale AB Experiments

9E - Stream Mining

9F - Large Scale Machine Learning

9F - Reinforcement Learning

Session 10 -- Machine Learning Lab III

10A - Netflix Challenge

10B - Ensembling examples

19C - Deep Learning with Tensor Flow

Session 11 -- Delegate Presentations

11A - Each delegate (or group of delegates) will have 5 minutes to present a Data Science Problem

11B - Devise a solution based on concepts taught in this training

11C - Feedback from the audience

Session 12 -- Networking


Salient Features

Comprehensive and State-of-the-art training in Data Analytics

Small Group -- Max 15. Opportunity to meet and mingle

Opportunity for a lot of group discussions and a chance to talk about your own work for 5 minutes in front of the group

Expert's Opinion

"Dr. Zaidi is one of Australia's leading young applied machine learning researchers. He has a superior grasp of algorithms and their use, and and this is well reflected in his choice of material and its clear presentation. This is an outstanding course."

Prof. Wray Buntine, Director of Masters of Data Science at Monash University

"This was the most enjoyable and informative course I have attended. Nayyar's in-depth knowledge in all the algorithms are reflected in the easy and simple ways he was able to articulate its use, strength and weakness. The course was complimented with good examples, and Nayyar's continues engagements with the participants created a group learning environment mutually beneficial to each other. I would strongly recommend this course to everyone who are keen on applied Data Science."

Dr. Dickson Lukose, Chief Data Scientist, GSC Agile

Testimonials

Following are selected testimonails, browse many more at: http://www.datasmelly.com/trainingAppliedML.html

"There was a lot of great material in the workshop; but I think that the most valuable part was Nayyar's ability to cover such a vast amount of material and methods and give an intuitive understanding of each one. I'm not sure that people realise it, but it takes a lot of effort and concentrated study to boil these models down to an intuitive approach which was maybe taken for granted by some of the participants. I have taken a couple other courses like this in Sydney. This one really really stands out; it is valuable information and you can see that its the quality of information and understanding you would expect from an academic. The other courses are money grabs for using R/python to solve kaggle and its really sad. I think maybe some people just want to be told how to use sklearn and don't care to understand how it actually works. Maybe this would be more profitable for you... but it would be sad if this course had to drop to that level."

Drew Harris, Quant, Epoch Capital

"We signed up for the Data Smelly course on Machine Learning to provide key members of our team with a solid foundation in Machine Learinng. We weren't disappointed. The two day course proved to be a great 'route-map' through the subject, providing an overview which covered all the main techniques and areas of interest. Nayyar was a great teacher too - animated and clearly excited by his subject. I'd highly recommend this course to anyone from a technical background who wants to learn more about how machine learning might be applied to their industry."

Max van Someren, Technology Development Manager, Austal

"A good grounding of the theory surrounding machine learning. Some insight into application and strategy of use. Thanks for putting on an interesting course. Good course material and a good insight into machine learning."

Peter Lyons, Origin Energy

"Dr Nayyar Zaidi is an enthusiastic facilitator and an excellent data scientist. His courses blend theory and practice, with practical hands-on exercises, and a chance to network with like-minded data practitioners. The best thing about Nayyar's courses is his ability to distill industrial applications of data science into easy-to-understand anecdotes and take-home insights for us."

Marc Cheong, Lecturer, Monash University

Frequent Questions

Why should I attend this course?

Good question! Let us ask you some counter questions.

1) Are you interested in exploring Machine Learning with some breath and depth?
2) Are you curious about the inner workings of most analytic algorithms?
3) Do you want to understand how machines learn from data?
4) Trying to figure out the latest trends in Analytics?
5) Interested in building a superior Machine Learning algorithm for your product or application?
5) Want a through exposition to Machine learning, but too busy to read all the books, research papers and blogs?
If answer to any of the above questions is yes, then you should attend this course.

How is this course different from others?

There are not many courses on Machine Learning, most are offered as part of post-graduate degree or diploma by universities. Non-academic units have a too narrow focus on certain technologies, for example, 'Machine Learning with R' or 'Machine Learning with Microsoft Technologies', etc. The extra layer of technology around the algorithms confuses the underlying message. We have designed this course around the core concepts and fundamental principles -- conveyed in a total technology agnostic way. The underlying concepts are taught through mathematical notations.

Do I need a deep Math background?

No, elementary (or high school) level Maths is desirable, but not necessary. Module 1 covers the background in Statistics and Linear Algebra that should act as a refresher course.

Do I need to bring my laptop?

Yes, there are four Laboratories where practical elements of Machine Learning will be illustrated. It will be beneficial if you bring your laptop, to do exercises on your computer.

Do I need to know computer programming?

For Labs, Yes. For other sessions, No. The practical component of the course, requires you to manipulate the data, train model, evaluate your learning algorithm, etc. You should know basic concpets of programming such as loops, variables, functions and classes.

I am not a Python programmer?

That is absolutely fine. We have chosen Python over C/C++, Java, R and Matlab, simply because it is easy to grasp. The first lab of the day will give you a good overview of the data structures and programming constructs of Python. So if you are a non-Python programmer, this will be an opportunity for you to learn.

What does course-kit consist of?

1) Book consisting of printed slides (over 300 pages)
2) Certificate of Attendance (posted in 2-3 weeks after attendance)
3) Welcome pack

Who will deliver this unit?

This course will delivered by a 'Principle Data Scientist' (highest designation at DataSmelly) -- the coordinator will have a Ph.D in Machine Learning or related area and over six years of research and development experience.

Share with friends

Date and Time

Location

Level 7

757 Ann St Fortitude Valley QLD 4006

Brisbane, QN 4006

Australia

View Map

Save This Event

Event Saved