https://www.eventbrite.co.uk/e/training-introduction-to-deep-neural-networks-tickets-77315405459
Speakers: Dr James V Stone, Dr Stephen J Eglen, Mr Lancelot da Costa
Requirements: Working knowledge of vector, matrices and differentiation. For practical exercises, working knowledge of Python will be assumed. Students should bring their own laptops to the lab session.
Cancellation: Please note we have introduced a new cancellation policy which you can review here
The aim of this workshop is to provide an introduction to deep learning methods. No prior experience of deep learning/neural networks is required. The workshop will be mostly lectures followed by a lab session.
09:30-10:00 Arrival
10:00-11:00 Inroduction: Deep Learning and AI: What it is, what it can, and cannot do. (JVS) slides
11:00-12:00 Overiew: perceptrons and feature detectors (SJE) slides
12:00-13:00 Lunch
13:00-14:00 Backprop: how it works (and how it fails). (JVS) slides
14:00-15:00 Dimensionality reduction. (LDC) slides
15:00-15:15 Break
15:15-16:45 Using python for networks.
Please install python on your laptop; we recommend Anaconda to install all the prerequisites. If you prefer, you can install miniconda, and then install the following packages:
conda install numpy matplotlib spyder jupyter
- No hidden layer practical/xor.py
- One hidden layer practical/main.py
- MNIST in Keras
Artificial Intelligence Engines
Deep Learning with Python (or in R)