BEGIN:VCALENDAR VERSION:2.0 PRODID:icalendar-ruby CALSCALE:GREGORIAN BEGIN:VEVENT DTSTAMP:20260501T114623Z UID:7vWNbA DTSTART;VALUE=DATE:20161109 DTEND;VALUE=DATE:20161110 CLASS:PUBLIC CREATED:20161018T011937 DESCRIPTION: On November 9\, join 180+ Pythonistas and dive deeper into neu ral networks: Word2vec and TensorFlow. \n\n Udemy\, our sponsor\, will be providing food and drinks! RSVP closes at 1p Nov 9. There will be no recording and walk-ins at this meetup. \n\n Lightning Talks \n\n \n Geospa tial data formats in Python by Arjun Attam \n Caching Django model changes with django-diffs by Sam Bolgert \n Feature Engineering using SKLearn-Pa ndas by Ramesh Sampath \n \n\n Talk #1: Word2vec algorithm: made as simple as possible\, but no simpler \n\n SUMMARY \n\n This talk will give a Pyth onic introduction to the word2vec algorithm. Word2vec\, translating words (strings) to vectors (lists of floats)\, is a relatively new algorithm whi ch has proved to be very useful for making sense of text data. You will ga in a conceptual understanding of the algorithm and be empowered to try it out on your favorite collection of text data. \n\n DESCRIPTION \n\n “You shall know a word by the company it keeps” is a common refrain in natur al language processing (NLP). word2vec is a simple neural network that lea rns which words tend to co-occur and embeds the words in a vector space. F rom these word embeddings\, it is possible to use distance measures to com pare words\, find neighbors by clustering\, and add/subtract words to expl ore relationships between concepts. Actually\, word2vec is a general purpo se algorithm that allows any sequential data to be encoded into meaningful vectors - including emojis! \n\n BIO \n\n Dr. Brian Spiering is a faculty member at GalvanizeU\, which offers a Master of Science in Data Science. His passions are natural language processing (NLP)\, deep learning\, and b uilding data products. He is active in the San Francisco data science comm unity through volunteering and mentoring. \n\n Talk #2: Recurrent neural n etworks with TensorFlow \n\n SUMMARY \n\n In this presentation you will be introduced to recurrent neural networks and the TensorFlow routines used for this type of machine learning. We will setup a model to classify two t ypes of earthquakes. At the end of the talk you will have learned what an RNN is and when to use it. \n\n DESCRIPTION \n\n Time-series data is seen in many places\, from a heart rate monitor to the variations in a star’s brightness. A great tool to model time-series is a recurrent neural netwo rk. This presentation will describe this type of model and why it works wi th this type of data. As an example\, we will use the earthquakes dataset from the UCR Time Series Classification Archive. Using TensorFlow\, we wil l set up an RNN model to classify types of earthquakes. In addition\, we w ill use TensorBoard to visualize the steps of the modeling process. \n\n B IO \n\n David Clark has a background in astrophysics\, where he used Pytho n extensively to analyze astronomical data. He recently transitioned caree rs to data science. Currently he is doing consulting for two startups. At Palo Alto Scientific\, Inc.\, he uses the machine learning library TensorF low to model sensor data from a wearable and infer a runner’s performanc e. He is also doing work for Quantea\, Inc.\, making a dashboard using the Python libraries Bokeh and Pandas. \n\n Agenda: \n\n 6:00p - Check-in and mingle\, with pizza and beer provided by our generous sponsor Udemy! \n\n 7:05p - Welcome \n\n 7:10p - Talk #1 and Q&\;A \n\n 7:50p - Announceme nts and lightning talks \n\n 8:10p - Talk #2 and Q&\;A \n\n 8:50p - Mor e mingling \n\n 9:30p - Doors close \n LAST-MODIFIED:20240729T041358 LOCATION:Udemy\, 600 Harrison St\, San Francisco\, CA 94107 ORGANIZER:mailto:grace@pybay.com SUMMARY:Learn about two takes on neural networks URL;VALUE=URI:https://ti.to/sf-python/LearnAboutTwoTakesOnNeuralNetworks URL;VALUE=URI:https://ti.to/sf-python/LearnAboutTwoTakesOnNeuralNetworks END:VEVENT END:VCALENDAR