ONLINE COURSE – Machine Learning and Deep Learning using Python (PYML01) This course will be delivered live
9 December 2020 - 10 December 2020£275.00
This course will now be delivered live by video link in light of travel restrictions due to the COVID-19 (Coronavirus) outbreak.
This is a ‘LIVE COURSE’ – the instructor will be delivering lectures and coaching attendees through the accompanying computer practical’s via video link, a good internet connection is essential.
TIME ZONE – Western European Time +1 – however all sessions will be recorded and made available allowing attendees from different time zones to follow a day behind with an additional 1/2 days support after the official course finish date (please email firstname.lastname@example.org for full details or to discuss how we can accommodate you).
Python is one of the most widely used and highly valued programming languages in the world, and is especially widely used in machine learning and for deep learning. In this two day course, we provide an introduction to machine learning and deep learning using Python. We begin by providing an overview of the machine learning and deep learning landscape, and discuss the prominent role that Python has come to play in this area. We then turn to machine learning in practice, and for this, we will primarily using the widely used and acclaimed scikit-learn toolbox. We begin with binary and multiclass classification problems, then look at decision trees and random forests, then look at unsupervised learning methods, all of which are major topics in machine learning. We then cover artificial neural networks and deep learning. For this, we will using the PyTorch deep learning toolbox. Here, we will cover the relatively easy to understand multilayer perceptron and then turn to convolutional neural networks.
THIS IS ONE COURSE IN OUR PYTHON SERIES – LOOK OUT FOR COURSES WITH THE SAME COURSE IMAGE TO FIND MORE IN THIS SERIES
This course is aimed at anyone who is interested in using R for data science or statistics. R is widely used in all areas of academic scientific research, and also widely throughout the public, and private sector.
Venue – Delivered remotely
Time zone – UK time
Availability – 20 places
Duration – 2 days
Contact hours – Approx. 15 hours
ECT’s – Equal to 1 ECT’s
Language – English
PLEASE READ – CANCELLATION POLICY: Cancellations are accepted up to 28 days before the course start date subject to a 25% cancellation fee. Cancellations later than this may be considered, contact oliverhooker@pRstatistics.com. Failure to attend will result in the full cost of the course being charged. In the unfortunate event that a course is cancelled due to unforeseen circumstances a full refund of the course fees will be credited.
Dr. Mark Andrews
Works at – Senior Lecturer, Psychology Department, Nottingham Trent University, England
Teaches – Introduction to statistics using R and Rstudio; Introduction data visualization using GG plot 2; Introduction data wrangling using R and Rstudio; Introduction to generalised linear models using R and Rstudio; Introduction to mixed models using R an d Rstudio; Introduction to Bayesian data analysis for social and behavioural sciences using R and Stan; Structural Equation Models, Path Analysis, Causal Modelling and Latent Variable Models Using R; Generalised Linear, Nonlinear and General Additive Models; Python for data science, machine learning, and scientific computing
Mark Andrews is a Senior Lecturer in the Psychology Department at Nottingham Trent University in Nottingham, England. Mark is a graduate of the National University of Ireland and obtained an MA and PhD from Cornell University in New York. Mark’s research focuses on developing and testing Bayesian models of human cognition, with particular focus on human language processing and human memory. Mark’s research also focuses on general Bayesian data analysis, particularly as applied to data from the social and behavioural sciences. Since 2015, he and his colleague Professor Thom Baguley have been funded by the UK’s ESRC funding body to provide intensive workshops on Bayesian data analysis for researchers in the social sciences.
This course will be hands-on and workshop based. Throughout each day, there will be some brief introductory remarks
for each new topic, introducing and explaining key concepts.
The course will take place online using Zoom. On each day, the live video broadcasts will occur between (UK local time)
All sessions will be video recorded and made available to all attendees as soon as possible, hopefully soon after each 2hr session. Attendees in different time zones will be able to join in to some of these live broadcasts, even if all of them are not convenient times. By joining any live sessions that are possible, this will allow attendees to benefit from asking questions and having discussions, rather than just watching prerecorded sessions. Although not strictly required, using a large monitor or preferably even a second monitor will make the learning experience better. All the sessions will be video recorded, and made available immediately on a private video hosting website. Any materials, such as slides, data sets, etc., will be shared via GitHub.
Assumed quantitative knowledge
We will assume familiarity with some general statistical and mathematical concepts such as matrix algebra, calculus,probability distributions. However, expertise with these concepts are not necessary. Anyone who has taken anyundergraduate (Bachelor’s) level course in mathematics, or even advanced high school level, can be assumed to havesufficient familiarity with these concepts.
Assumed computer background
We assume familiarity with using Python, general purpose programming in Python, and numerical programming in
Python. Note that both of these topics covered comprehensively in two preceding two-day courses, which together will provide all the computing prerequisites for this course.
Equipment and software requirements
Attendees of the course must use a computer with Python (version 3) installed. All the required software, including
Python itself, the development and programming environment tools, and the Python packages, are free and open
source and are available on Windows, MacOs, and Linux. Instructions on how to install and configure all the software will be provided before the start of the course. We will also provide time during the workshops to ensure that all software is installed and configured properly. For deep learning, we will also make use of Google’s Colaboratory https://colab.research.google.com/, which will give us access to graphical processing units.
UNSURE ABOUT SUITABLILITY THEN PLEASE ASK email@example.com
Wednesday 9th – Classes from 10:00 to 20:00
• Topic 1: Machine learning and Deep Learning Landscape. Concepts like machine learning, deep learning, big data,
data science have become widely used and celebrated in the last 10 years. However, their definitions are relatively
nebulous, and how they related to one another and to major fields like artificial intelligence and general statistics are not simple matters. In this introduction, we briefly overview the field of machine learning and deep learning, discussing its major characteristics and sub-topics, and also discuss the prominence of Python in the area.
• Topic 2: Classification problems. Classification problems is one of the bread and butter topics in machine learning, and is usually the first topic covered in introductions to machine learning. Here, we will cover image classification (itself a “hello world” type problem in machine learning), and particularly focus on logistic regression and support vector machines (SVMs).
• Topic 3: Decision trees and random forests. Decision trees are a widely used machine learning method, particularly for classification. Random forests are an ensemble learning extension of decision trees whereby large number of decision tree classifiers are aggregated, which often leads to much improved performance.
Thursday 10th – Classes from 10:00 to 20:00
• Topic 4: Unsupervised machine learning. Unsupervised learning is essentially a method of finding patterns in
unclassified data. Here, we will look at two of the most widely used unsupervised techniques: k-means clustering
and probabilistic mixture models.
• Topic 5: Introducing artificial neural networks and deep learning with PyTorch. Python provides many popular
libraries for artificial neural networks and deep learning. These include Keras and TensorFlow. Here, we will use
PyTorch, which is a relatively new but increasingly high-level neural network model building and training
language. These models often use graphical processing units (GPUs) for computing. Given that most personal
computers don’t have adequate GPUs, we will use Google’s Colaboratory https://colab.research.google.com/,
which is a free Python Jupyter notebook service from Google.
• Topic 6: Multilayer perceptons. Multilayer perceptrons are very powerful, yet relatively easy to understand,
artificial neural networks. They are also the simplest type of deep learning model. Here, we will build and train a multilayer perceptron for a classification problem.
• Topic 7: Convolutional neural networks. Convolutional neural networks (CNNs) have proved high successful at
image classification, primarily due to their translation invariance, which is highly suitable for computational vision. Here, we use PyTorch to build and train a CNN for image classification.