What we're about

Hands on meetups (lectures, classes, demo talks) with free compute time sponsored by Amazon AWS. We focus on giving members the opportunity to learn and share with the rest of the programming community.

Upcoming events (4+)

Deep Learning Study Group

Link visible for attendees

Deep learning is evolving quickly. Important new developments are appearing daily. This group attempts to keep up by reading and discussing current deep learning literature. This meetup uses discussion among the participants to speed understanding of current research results. That requires that some participants read the paper before attending. Anyone is welcome to attend and listen without reading the paper. If nobody reads the paper the meeting will be short.

Papers that we're reading, code that participants generate and other random stuff can be found at github site for the group.

mike-bowles/hdDeepLearningStudy (https://github.com/mike-bowles/hdDeepLearningStudy)

Our discord page has paper for next week, papers being considered and other discussion of deep learning: https://discord.gg/HuWVmMgmqS

https://arxiv.org/pdf/2110.00966.pdf - Translating Images into Maps

The event will be broadcast to Hacker Dojo classroom to facilitate face-to-face attendance. 855 Maude Ave, Mountain View, CA

Rigorous Statistics for Academics and Practitioners

Link visible for attendees

This lecture series by Michal Fabinger should cover the fundamentals of statistics over the coming months, including advanced topics such as causal inference.

Current topic: Linear Regression (Lectures 1, 2, 3,4,and 5)

Linear regression models

(1) Normal linear model

Topics discussed: assumptions of the normal linear model, distribution
of the error term, least-squares estimator of the parameter vector and
its distribution, estimator of the variance of the error term and its
distribution, confidence intervals and hypothesis tests for the
model's parameters, Student's t-distribution, and chi squared
distribution.

(2) Linear model with heteroscedasticity

Topics discussed: assumptions of the linear model with
heteroscedasticity, distribution of the error term, least-squares
estimator of the parameter vector and its asymptotic distribution,
confidence intervals and hypothesis tests for the model's parameters.

The lectures are a part of a 2022 lecture series that aims to build a solid foundation of statistics knowledge for the participants. To sign up for the whole lecture series, please fill out this form:

https://form.typeform.com/to/rep1RuEc

The material should later help the participants understand scientific articles that use probability theory and statistics. Such knowledge is useful both for machine learning and data science practitioners and for those on an academic path (undergraduates, graduate students, postdocs, or faculty members). The content is similar to the corresponding course at the Acalonia school.

To sign up for the whole lecture series including notes, quizzes, and assignments, please submit this form:

https://form.typeform.com/to/rep1RuEc

The Zoom link for Thursday 8 pm PDT are no longer public because of Zoom bombing and abuse. Register above in advance for link.

Deep Learning Study Group

Needs a location

Deep learning is evolving quickly. Important new developments are appearing daily. This group attempts to keep up by reading and discussing current deep learning literature. This meetup uses discussion among the participants to speed understanding of current research results. That requires that some participants read the paper before attending. Anyone is welcome to attend and listen without reading the paper. If nobody reads the paper the meeting will be short.

Papers that we're reading, code that participants generate and other random stuff can be found at github site for the group.

mike-bowles/hdDeepLearningStudy (https://github.com/mike-bowles/hdDeepLearningStudy)

Deep Learning Study Group

Needs a location

Deep learning is evolving quickly. Important new developments are appearing daily. This group attempts to keep up by reading and discussing current deep learning literature. This meetup uses discussion among the participants to speed understanding of current research results. That requires that some participants read the paper before attending. Anyone is welcome to attend and listen without reading the paper. If nobody reads the paper the meeting will be short.

Papers that we're reading, code that participants generate and other random stuff can be found at github site for the group.

mike-bowles/hdDeepLearningStudy (https://github.com/mike-bowles/hdDeepLearningStudy)

Past events (893)

Rigorous Statistics for Academics and Practitioners

This event has passed

Photos (145)