Neural Networks and Deep Learning for Life Sciences and Health Applications
This course offers an introduction to topics of neural networks and deep learning using Tensorflow. There is a focus on applications in life sciences. The course is recommended for professionals as well as beginners with a suitable background and interests.
At a glance
Qualification: Certificate of attendance
Duration: 30-36 contact lessons
Costs: CHF 760.00
Comment on costs: 760 regular
Location: Lagerstrasse 41
Language of instruction:
Objectives and content
This course is for professionals as well as students.
It is addressed to people who are willing to learn what deep learning is. You should be someone who has some background in programming (not necessarily in Python) and some background in mathematics. If you are a beginner, we will cover the basics you need, but you may need to work a bit more on your own during the classroom lectures.
Review of Python and numpy, Matplotlib, review of linear algebra, computational graphs, introduction to tensorflow, network with one neuron, logistic and linear regression with one neuron, neural networks with many layers, overfitting, weights initialization, gradient descent algorithm, dynamical learning rate decay, optimizers (Momentum, RMSProp, Adam), regularization: L1, L2 and dropout, metric analysis, hyperparameter tuning, grid search, random search, bayesian optimization, coarse to fine optimization, parameter search on a logarithmic scale
Enquiries and contact
Umberto Michelucci (main lecturer)
Offered in cooperation with
Umberto Michelucci (Helsana)
Information for applicants
Starting October 2018