Join us at one of our workshops
We run many workshop series during the academic year covering all aspects of data science
Over the course of the past year we hosted a variety of events. Each event attracted over 40 attendees on average, and over 300 students took part in our talent development initiatives and corporate events. In the upcoming year, we seek to maintain engagement amongst our members while increasing our event offering.
Our workshop series cover various topics including data analysis, data visualisation, machine learning, and programming both in R and Python, the latter being a member favourite.
Our workshops are usually 1 hr 30 mins long and there will be helpers from the society to assist you during the lesson. Furthermore, there will be refreshments provided at the end!
ICDSS GUEST SPEAKER
We would like to welcome Prof. Wolfram Wiesemann to ICDSS
*From Descriptive to Prescriptive Analytics*
Recent years have seen tremendous progress in descriptive analytics (using data to understand the past) and predictive analytics (using data to understand the future). In this workshop I will argue that the commonly neglected domain of prescriptive analytics (using data to make decisions) is at least of equal importance. I will provide a high-level overview of the current state-of-the-art in prescriptive analytics, with a focus on the areas of linear optimisation, discrete optimisation and nonlinear optimisation.
Wolfram Wiesemann is Associate Professor of Management Science and Operations as well as Fellow of the KPMG Centre for Advanced Business Analytics at Imperial College Business School, London. Before joining the faculty of Imperial College Business School in 2013, he was a post-doctoral researcher at Imperial College London (2010-2011) and an Imperial College Research Fellow (2011-2012). He was a visiting researcher at the Institute of Statistics and Mathematics at Vienna University of Economics and Business, Austria, in 2010, the Computer-Aided Systems Laboratory at Princeton University, USA, in 2011, and the Industrial Engineering and Operations Research Department at Columbia University, USA, in 2012. Wolfram’s research interests revolve around the methodological aspects of decision-making under uncertainty, as well as applications in operations management, energy and finance.
Sign up for the talk on our Events page!
Check out when and where our workshops take place
Workshop #01 (19/10/17)
Workshop #02 (28/11/17)
Workshop #S1 (02/11/17)
Workshop #03 (28/02/18)
- Theory: Linear Models
- Application: Finance - Simple Beta Hedging
- Codelab: Vanilla Python
- This is a supplementary workshop
- The whole workshop will cover scientific Python
- Convolutional Neural Networks
- Theory: Neural Networks
- Application: ImageNet - state-of-the-art
- Codelab: neural network from scratch & tensorflow equivalent
Workshop #04 (07/03/18)
Guest Talk (22/03/18)
- Advanced Machine Learning
- Codelab: *scikit-learn* and *keras*
Sign up to our workshops at our Events page! Click below:
All the handouts and presentation for our workshops can be found here!
The aim of this workshop is to introduce you to Data Science and especially Linear Models. We will answer questions, such as "what is a model?" and "why linear in particular". Then, we will go through some applications, starting with a Simple Beta Hedging algorithm, usually used in finance. Finally, we will get our hands dirty with implementing this algorithm in vanilla Python and then using off-shelf Machine Learning frameworks, such as scikit-learn and TensorFlow.
- Basic linear algebra
- Any experience with programming
Get the workshop materials from the github link below:
During a two hour event you will be working in small groups and learn the essentials of Numpy, Pandas, Matplotlib and Scipy. If you are just getting started with the scientific Python stack, this is the perfect learning opportunity! Attending this workshop will equip you with the skills necessary to follow our future machine learning oriented events easily.
NOTE: this event is aimed specifically at people unfamiliar with the scientific Python stack. Attendance is not required to get the final ICDSS certificate.
In this workshop we will cover the basics of Convolutional Neural Networks. We will explore the application of convolution operation to image processing. We will then see how it can be integrated into the neural network framework and why this type of network greatly outperforms all previous machine learning algorithms in image processing tasks. Finally, we will learn some practical aspects of implementing ConvNets, including transfer learning.
- Linear Models and Feedforward Neural Networks
- Linear Algebra (vector & matrix operations)
- Scientific Python
In this workshop we will cover the most frequently used High-Level Machine Learning libraries, *scikit-learn* and *keras*. The focus of this workshop will be on how to the implementation of abstract models in code, using the universal fit-predict-score pattern most machine learning APIs follow. Multiple sandbox projects will be attempted, including multivariate regression, classification and time-series forecasting.
- Linear Models
- Scientific Python (NumPy & SciPy)
- Neural Networks
In this workshop we will cover the fundamental theory and applications of Neural Networks. We will derive the Bacpropagation Learning Algorithm and implement a network using NumPy, exploiting computational graph theory. The Neural Network approximator will be compared to a simple Linear Model on a binary classification application for Computer Vision.
- Linear Models
- Scientific Python
- Calculus (chain rules, partial derivatives)
- Linear algebra
Our Social Media Pages
Telephone: 020 7594 8060
Imperial College London,
South Kensington Campus,