What we're about

San Diego Machine Learning is an active group with many events. We are machine learning practitioners, students, and enthusiasts who want to get together to share, discuss and try various techniques -- and possibly hack on the occasional challenge. We have a wide range of experience levels with machine learning either through work, school or personal exploration. We currently have a weekly book club, project time, and a mix of other ML webinars. Everyone is welcome!

For more information about our data science talks and ML book club, please visit our GitHub respositories: https://github.com/SanDiegoMachineLearning/talks and https://github.com/SanDiegoMachineLearning/bookclub

Upcoming events (3)

Hands-on Machine Learning -- Classification

Online event

Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow (2nd Edition) by Aurélien Géron

Classification
Discussion leader: Vibhu Sapra
We will finish our discussion from the previous week of the end to end machine learning process. Then we will discuss how to model classification problems, and the metrics used to evaluate them. This material is in chapter three of the book.

The SDML book club will be meeting Saturdays to discuss one chapter each week. The HOML book (https://www.oreilly.com/library/view/hands-on-machine-learning/9781492032632/ ) is available from different booksellers. Make sure to get the second edition with the color cover, not the first edition with the red cover. This is simply one of the best data science books out there. The book covers all of the core concepts from basics like what is machine learning and linear regression to advanced models like reinforcement learning and GANs. This material will provide a solid foundation for beginners, and further the understanding for more experienced data scientists.

=================
Agenda
=================
- 12:00 - 12:15 pm -- Arrival and socializing/breakouts
- 12:15 - 12:45 pm -- Continuation of End-to-End Machine Learning Project
- 12:45 - 1:30 pm -- Classification
- Time permitting -- Additional breakouts

Links to chapter notes and videos of prior meetups are available on the SDML GitHub repo https://github.com/SanDiegoMachineLearning/bookclub

SDML members will be taking turns leading the chapter discussions. If you are interested in taking a chapter, send me a message. (A few people have told me I did not get their emails. If you don't hear back from me right away, please message me again.)

=================
Location
=================
This will be an online meetup until further notice.

=================
Questions?
=================
Join our slack channel or leave a comment below if you have any questions about the group or need clarification on anything.
https://join.slack.com/t/sdmachinelearning/shared_invite/zt-6b0ojqdz-9bG7tyJMddVHZ3Zm9IajJA

Data Science Project/Competition Collaboration Time [Virtual]

* We will start about 1:30 pm PDT, after the book club ends *

Come join us for an open discussion about data science projects with experienced practitioners. We may talk about competitions on Kaggle, or you can bring another coding issue or project you are working on, and ask questions in a friendly office hours setting. This ask-me-anything session is open to everyone, from beginning learners to seasoned data scientists.

This weekly meetup will be a venue to discuss approaches to machine learning projects, learn data science techniques, and sharpen your coding skills. It is open to all levels.

=================
Location
=================
This will be an online meetup until further notice.

=================
Questions?
=================
Join our slack channel if you have any questions about the group or need clarification on anything.
https://join.slack.com/t/sdmachinelearning/shared_invite/enQtNDk0MTcwODIxNzE5LWY1YjFiYmI3MjI0Yzc1ZDU0NzY3NzY2NmY0ODZhMzI0NjRiNGIwNTM1ZDIzOGU2OTIwZWIxZjM3ZmNlMzNkYzI

Evaluating Robustness of Neural Networks [Virtual]

Online event

Evaluating Robustness of Neural Networks
by Lily Weng

Abstract:
The robustness of neural networks to adversarial examples has received great attention due to security implications. Despite various attack approaches to crafting visually imperceptible adversarial examples, little has been developed towards a comprehensive measure of robustness. In this talk, Weng will introduce several robustness quantification frameworks for deep neural networks against both adversarial and non-adversarial input perturbations, including the first robustness score CLEVER, efficient certification algorithms Fast-Lin, CROWN, CNN-Cert, and probabilistic robustness verification algorithm PROVEN. The proposed approaches are computationally efficient and provide a good quality of robustness estimate/certificate as demonstrated by extensive experiments on MNIST, CIFAR and ImageNet.

Bio:
Lily Weng is an Assistant Professor in the Halicioglu Data Science Institute at UC San Diego with an affiliation to the CSE department. She has broad research interest in the intersection of machine learning, optimization and reinforcement learning, with applications in cybersecurity and healthcare. Her vision is to make the next generation AI systems and deep learning algorithms more robust, reliable, trustworthy and safer. She has worked on developing efficient algorithms as well as theoretical analysis to quantify robustness of deep neural networks. She received her PhD in Electrical Engineering and Computer Sciences (EECS) from MIT in 2020, and her Bachelor and Master degree both in Electrical Engineering at National Taiwan University in 2011 and 2013.

=================
Agenda (Pacific Daylight Time, UTC -07)
=================
- 5:30 - 5:40 pm -- Gathering and introductions
- 5:40 - 6:30 pm -- Talk
- 6:30 - 7:00 pm -- Q & A, discussion

Links to slides and videos of meetup presentations are available on the SDML GitHub repo https://github.com/SanDiegoMachineLearning/talks

=================
Questions?
=================
Join our slack channel or leave a comment below if you have any questions about the group or need clarification on anything.
https://join.slack.com/t/sdmachinelearning/shared_invite/zt-6b0ojqdz-9bG7tyJMddVHZ3Zm9IajJA

Past events (237)

Photos (62)