2. About the workshop
• Helping you get started with ML
• Introducing key points and concepts
• hands-on examples
• Goal is not to become a ML researcher
• But you can learn enough to use in your own research
• and to know where to go next if you were interested
3. What is Machine
Learning
• Common theme is to solve a prediction problem:
• given an input x,
• predict an “appropriate” output y
• Examples:
• Email spam detection: X = email message Y = “spam” or
“not-spam”
• Medical diagnosis: X = symptoms Y = “healthy” or
“disease 1” or “disease 2”…
• Stock price prediction: X = history of prices Y = next day’s
price
• Object detection: X = an image Y = What is in the photo
and where is it
4. Elements of an ML solution
• The data
• Encoding ->Features
• The output (
• Split
• The model
• The parameters
14. References and resources
• Introduction to Machine Learning with Python: A Guide for Data
Scientists by Andreas C. Müller, Sarah Guido
• Kaggle
• deeplearning.ai
• Bloomberg (David Rosenberg)
• https://www.tensorflow.org/resources/learn-ml
Editor's Notes
Took from Bloomberg’s course
Any function can be approximated,
G = non linearity