4C16/5C16 is course on Machine Learning (ML), with a focus on Deep Learning. It is a fourth and fifth year module offered by the Electronic & Electrical Engineering department to the undergraduate students of Trinity College Dublin.
Although Deep Learning has been around for quite a while, it has recently become a disruptive technology that has been unexpectedly taking over operations of technology companies around the world and disrupting all aspects of society. When you read or hear about AI or machine Learning successes in the news, it really means Deep Learning successes.
The course starts with an introduction to some essential aspects of Machine Learning, including Least Squares, Logistic Regression and a quick overview of some popular classification techniques.
Then the course dives into the fundamentals of Neural Nets, including Feed Forward Neural Nets, Convolution Neural Nets and Recurrent Neural Nets.
The material is constructed in collaboration with leading industrial practitioners including Google, YouTube and Movidius, and students will have guest lectures from these companies.
We have designed a unique environment specifically for this course so that students can learn best industry practices.
Our web platform can transparently connect students to a Google Cloud Platform cluster via web based terminal/editor/Jupyter sessions. Labs use the Keras framework and are automatically assessed using Git to give immediate feedback.
Labs include designing and training various DNN for image classification challenges, self driving car (simulator) and text processing.
handouts and videos from last year an be found here
It is recommended to students to refresh their knowledge of Python 3 prior to starting 4C16. Some useful resources are listed in the document below:
Hugh Denman's slides about python 3 and the 4C16 lab system is available here:
George Sterpu is compiling a list of frequently asked questions & answers on his webpage:
- pdf slides
- video (lecture 12/09/2018)
- no video for lecture 13/09/2018
- pdf tutorial on linear algebra
- pdf tutorial on least squares
- video (tutorial 17/09/2018)
k-NN, Decision Trees, SVM and Kernel Trick
- pdf slides
- video (lecture 01/10/2018)
- video (lecture 03/10/2018)
- no video for lecture 04/10/2018
- pdf slides
- video (lecture 08/10/2018) - CNN
- video (lecture 17/10/2018) - visualisation pt1
- video (lecture 18/10/2018) - visualisation pt2
Nov 1st 11-12am, Robert Emmet Theatre, Trinity College Dublin
As Chief Software Architect Autonomous Driving Peter is a seasoned technical leader, with 27 years in development of distributed/embedded computing platforms. He currently leads the software team at Jaguar Landover responsibility for bringing Level 4 autonomy to Jaguar Landover’s products. Prior to this role, Peter was a Senior Principal Engineer at Intel, where he led the definition and development of numerous products such as Intel's in vehicle infotainment platforms and IoT Quark Product line. Peter has published two textbooks and holds 23 patents.
Nov 21st 4-5pm, Jonathan Swift Theatre, Trinity College Dublin
Professor Linda Hogan is an ethicist with extensive experience in research and teaching in pluralist and multi-religious contexts. Her primary research interests lie in the fields of inter-cultural and inter-religious ethics, social and political ethics, human rights and gender.
Nov 22nd 11-12am, Robert Emmet Theatre, Trinity College Dublin
Michaela is Principal Engineer and Engineering Director at Xilinx Ireland. She has over 20 years industry experience in FPGA and board-level design and networking. Her main areas of interest include data centers, high-level synthesis tools, high-speed network processing on FPGAs (100Gbps and beyond).
Nov 28th 6:30-7:30pm, Google Offices, Dublin
George Toderici is Tech Lead / Manager at Google. He received his Ph.D. in Computer Science from the University of Houston in 2007 where his research focused on 2D-to-3D face recognition, and joined Google in 2008. He now leads a team that focuses on creating a new state of the art class of algorithms in the domain of lossy image compression and beyond. Prior to this, he designed deep learning methods for video classification, annotation, embedding models and more.