The Graduate Division serves more than 13,000 students in over 100 graduate degree programs. We are here to help you from the time you are admitted until you complete your graduate program.
We're thrilled you're considering Berkeley for your graduate study. We offer more than 100 programs for master's, professional, and doctoral students to pursue their dreams.
Working toward obtaining your graduate degree at Berkeley is an exciting and challenging endeavor, but funding your graduate education shouldn’t be your greatest challenge.
We're here to support you as you progress through your degree, and help you understand the policies and procedures that inform your graduate education.
GradPro, the Graduate Writing Center, and the GSI Teaching & Resource Center can support you in your academic and professional development at all stages of your degree program and in preparing for your career.
The Office for Graduate Diversity provides support and services for prospective and continuing students in an effort to support and sustain a more diverse graduate student community.
Your gift allows us to deliver an inclusive, world-class experience to graduate students, so they can make a difference at Berkeley and beyond.
Back to All Events
The goal of this workshop is to build intuition for deep learning by building, training, and testing models in Python. Rather than a theory-centered approach, we will evaluate deep learning models through empirical results.
We start with a review of what deep learning is and then unpack what neural networks are and how they work. We then jump straight into Python, using the Keras library to build neural networks. We will explore how different architectures affect the performance of predicting handwritten digit images.
Lastly, we explore a specific flavor of neural networks, the convolutional neural network. We review how it’s different from a standard vanilla neural network, and build different architectures to test how well they perform on the classification of animal and vehicle image classification.
Prerequisites: D-Lab’s Python Machine Learning Fundamentals (6 hours) series or equivalent introductory machine learning knowledge.
Workshop Materials: https://github.com/dlab-berkeley/Python-Deep-Learning.