Intermediate Supervised Machine Learning (ONLINE LIVE TRAINING)

IntermediatePrerequisitesNew

The vast majority of data produced fits the criteria of labelled data (with either continuous of categorical labels); the machine learning task of discriminating classes (for categorical outputs) or predicting future values (continuous outputs) will be discussed in detail, focusing both on classical methods – k nearest neighbours, decision tree based methods and support vector machine – and on the importance and discriminative power of features.

The module will provide support in generating models (using R as programming environment), critically assessing the optimisation of hyperparameters and evaluating the usefulness of the model with respect to the initial question. The examples presented throughout stem from biological examples, yet the skills and critical assessment of outputs are transferrable.

If you do not have a University of Cambridge Raven account please book or register your interest here.

• Our courses are only free for registered University of Cambridge students. All other participants will be charged according to our charging policy.
• Attendance will be taken on all courses and a charge is applied for non-attendance, including for University of Cambridge students. After you have booked a place, if you are unable to attend any of the live sessions, please email the Bioinfo Team.
• Further details regarding eligibility criteria are available here.

• Graduate students, Postdocs and Staff members from the University of Cambridge, Affiliated Institutions and other external Institutions or individuals

• This is not an introductory course and participants should be very confident in programming in R as the course will build on this. Attendance at an introductory R course will not be sufficient experience and participants are expected to have significant prior experience with this language. Participants are also expected to have a prior awareness of basic machine learning principles and concepts.

Number of sessions: 2

• Decisions Trees
• Support Vector Machines
• K-nearest neighbour classifiers
• Regression
• Optimisation of hyperparameters
• Model Evaluation

Presentations, demonstrations and practicals

Participants will need an up to date installation of R and RStudio as well as a good internet connection. All data and material will be provided.

This is subject to change in line with the online training schedule.

• Free for registered University of Cambridge students
• £ 60/day for all University of Cambridge staff, including postdocs, temporary visitors (students and researchers) and participants from Affiliated Institutions. Please note that these charges are recovered by us at the Institutional level
• It remains the participant's responsibility to acquire prior approval from the relevant group leader, line manager or budget holder to attend the course. It is requested that people booking only do so with the agreement of the relevant party as costs will be charged back to your Lab Head or Group Supervisor.
• £ 60/day for all other academic participants from external Institutions and charitable organizations. These charges must be paid at registration
• £ 120/day for all Industry participants. These charges must be paid at registration
• Further details regarding the charging policy are available here

2

several times a year

• Introduction to R for Biologists (IN-PERSON)