Deep Learning 2-Day Workshop - March 2018

Silverpond

<H2>Deep Learning 2-Day Workshop</H2>
Venture into deep learning with this 2-day workshop that will take you from the mathematical and theoretical foundations to building models and neural networks in TensorFlow. You will apply as you learn, working on exercises throughout the workshop. To enhance learning, a second day is dedicated to applying your new skills in team project work. We will meet again in a few weeks for a “show and tell”, where attendees can share deep learning developments - our way to support your continued progress in machine learning.
This hands-on workshop is ideal for both data science and programming professionals, who are interested in getting started with deep learning and embarking on their first project.
 
<HR>
 
DAY 1 - 9AM – 5PM WED 7 MAR 2018 DAY 2 - 9AM – 5PM THU 8 MAR 2018
SILVERPOND OFFICE  Level 2, 382 Little Collins Street Melbourne, Australia
 
<H3>You have:</H3>
<UL>
<LI>
Basic Python skills
</LI>
<LI>
A willingness to learn mathematics
</LI>
</UL>
 
<H3>We'll cover:</H3>
<UL>
<LI>
Machine learning fundamentals
</LI>
<LI>
Building deep learning models in TensorFlow (with Python)
</LI>
<LI>
Representation Learning/Word Embeddings 
</LI>
<LI>
Convolutions/Pooling
</LI>
<LI>
Solving a simple neural network by hand to consolidate knowledge
</LI>
<LI>
Hands-on exercises in a collaborative environment
</LI>
<LI>
Using TensorFlow as a general computation engine
</LI>
</UL>
 
<H3>Breakdown:</H3>
Here’s what the days will look like:
<UL>
<LI>Day 1 - Fundamentals, Convolutions, Embeddings, Exercises.</LI>
</UL>
The first day will see us learn as a group, working through exercises and building up a solid base of knowledge around deep learning.
We will cover key concepts in the field and introduce them with examples.
<UL>
<LI>Day 2 - Group projects.</LI>
</UL>
The second day will see us consolidate our knowledge by working in small groups on complete projects. A few project options will be provided across image processing, natural language processing (NLP), and generative models.
This day will build real-world experience in deep learning model development.
<UL>
<LI>Show and Tell - Discussion evening.</LI>
</UL>
To conclude, the group will meet a few weeks later for a Show and Tell session. Attendees can share any deep learning projects in progress, interesting articles read, bounce ideas off one another or just discuss ideas they want to explore.
This casual gathering is an opportunity to touch base with fellow deep learning enthusiasts and support your continued growth in the field.
 
<H3>Outcomes include:</H3>
<UL>
<LI>
An intuitive understanding of the components of machine learning systems
</LI>
<LI>
Experience building neural networks in TensorFlow
</LI>
<LI>
Clear understanding of convolutions and representation learning
</LI>
<LI>
Experimenting with a model that learns representations of words
</LI>
<LI>
Practical real-world model development in TensorFlow
</LI>
</UL>
 
<DIV CLASS="chapter">
<DIV CLASS="content">
<H3>Requirements:</H3>
<UL>
<LI>
A laptop
</LI>
</UL>
 
More information: Feel free to email <A HREF="mailto:training@silverpond.com.au" TARGET="_blank" REL="nofollow noopener noreferrer">training@silverpond.com.au</A> with any questions you may have!
<H3> </H3>
<HR>
<H3>Workshop reviews</H3>
"I found this a fun introduction to deep learning fundamentals, tensorflow toolkit and how it can be applied to real world situations. Sometimes you just need a bit of a bootstrap to get your going with an emerging technology, and this course does just that." – Maree 
“The workshop was great and I would definitely recommend to everyone who wants to learn deep learning with real world examples. Basic concepts are introduced during the workshop and programming exercises are given to aid the learning.” – Selva
As the top “deep learningers” in the town, the organisers have profound knowledge and experience. They are also active in sharing their knowledge and getting more people interested. Their lecture notes are fascinating and can engage audiences of all levels. If you ever got buzzed by “deep learning”, here’s where you should go. – Fei
 
<HR>
<H3> </H3>
<H3>About Your Instructors </H3>
 
Noon van der Silk 
<IMG SRC="https://s.evbuc.com/https_proxy?url=http%3A%2F%2Fsilverpond.com.au%2Fimg%2Fteam%2Fnew_shoot%2FSilverpond-Noon-Silk-1.jpg&sig=ADR2i7-ZHxkj27IFEdTvkjUfDB8Vvl5nMQ">
Noon is a long-time programmer who recently obtained a Masters in Pure Mathematics from The University of Melbourne. He enjoys functional programming and thinking of fun and interesting applications of deep learning. He has previously been mistaken for a paper-reading robot.
 
Lyndon Maydwell
<IMG SRC="https://s.evbuc.com/https_proxy?url=http%3A%2F%2Fsilverpond.com.au%2Fimg%2Fteam%2Fnew_shoot%2FSilverpond-Lyndon-Maydwell-1.jpg&sig=ADR2i7-fpsicJKg-w7PcKOx6bIjmBctV9Q">
Lyndon can code his way out of a wet paper bag, and has done so in the past. He enjoys thinking of new and interesting ways to understand and work with ideas in deep learning and excels at expressing complicated concepts concisely (and occasionally writing those concepts down in esoteric programming languages).
 
Adel Foda
<IMG SRC="https://s.evbuc.com/https_proxy?url=http%3A%2F%2Fsilverpond.com.au%2Fimg%2Fteam%2Fnew_shoot%2FSilverpond-Adel-Foda-1.jpg&sig=ADR2i79d0JnLo81OonbXW34dko1HzJ7Ecg">
Adel is a data scientist and computational linguist at heart. His deep learning repertoire spans images, video, audio, and text. Adel has an interest in pedagogy and is a regular presenter at meetups and industry events on topics of applied science.
 
Martin Ingram
<IMG SRC="https://s.evbuc.com/https_proxy?url=http%3A%2F%2Fsilverpond.com.au%2Fimg%2Fteam%2Fnew_shoot%2FSilverpond-Martin-Ingram-1.jpg&sig=ADR2i79qBhig5-IMLgVI70YinTuYbv1-VQ">
Martin studied Physics at the University of Cambridge followed by an MSc in Computing Science from Imperial College London. He specialises in deep learning for computer vision and sports analytics. In his spare time, Martin enjoys predicting tennis matches - through mathematical modelling of course. 
 
</DIV>
</DIV>