Introduction:

Are you amazed by the recent breakthroughs of machine learning, but are unsure of how it works under the hood? Have you ever wondered how snapchat filters convert ordinary faces into works of art, or how Google can beat masters of board games?
If so, welcome to the Machine Learning Decal! In this course, you will discover how to analyze and manipulate data in Python, go over (and implement!) fundamental and practical statistical and deep learning learning models, as well as learn how to ask the right questions in order to tackle data-driven problems. The course content targets an audience who has experience programming and understands calculus, though motivated and interested students without a strong technical background are encouraged to apply.
No matter your background, data science and machine learning are infiltrating your field. More and more data are being created every day, and we will give you the skills to begin to make sense of it all.
We will be posting all materials for this course online. Feel free to follow along at https://github.com/mlberkeley/Machine-Learning-Decal-Fall-2018!

Prerequisites:

This class is a projects-based class with a machine learning bias. You are expected to have some programming or statistics backgrounds and so the material will be of greatest benefit to sophomores or those who have programming experience (CS61A, DATA 8, STAT 133, or equivalent) and understand math fundamentals (Math 53 and Math 54 or equivalent; EE16A or EE16B or equivalent). In the first week of class we will go over the fundamentals of python for data science. By the end of it, you can determine whether you are comfortable continuing through the course.

Note that this is not an easy class. The student facilitators intend to provide you with an overview of deep learning models with the goal of preparing you for industry and, if demonstrated superb interest, future machine learning competitions.

Homeworks:

There will be 7 homework assignments, assigned throughout the semester. Homeworks will be completed individually, with an emphasis on coding.

Projects:

At the end of class, there will be 1 final project which students should complete in groups of 3-4. Students can either work on their own time to finish this project, or they can attend and do a project during a hackathon period, where there will be mentors to help out. The purpose of the projects is to give you hands on experience manipulating, analyzing, and modeling data, with an emphasis on explaining choices of techniques.

Grading:

60% Projects (20% each)
40% Homeworks (10% each)
Sufficient attendance (see attendance section below)
In order to pass the class, you must meet the attendance requirement and earn at least a 70% cumulative score on the projects and homework

Attendance:

We will be keep track of attendance. In order to pass the course, you must come to AT LEAST 75% of the lectures (that is, 9 lectures at minimum). After your 3rd missed day of class, excused or unexcused, you will automatically be assigned a “no pass”.