BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:US/Eastern BEGIN:DAYLIGHT DTSTART:20210314T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20211107T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20220324T154253Z UID:F8B1FDD1-7D70-4D0D-9615-7650099EC845 DTSTART;TZID=US/Eastern:20210619T090000 DTEND;TZID=US/Eastern:20210619T123000 DESCRIPTION:Series Overview: From the book introduction: "Neural networks a nd deep learning currently provides the best solutions to many problems in image recognition\, speech recognition\, and natural language processing. "\n\nThis Part 1 and the planned Part 2 (winter or spring 2022\, to be con firmed) series of courses will teach many of the core concepts behind neur al networks and deep learning.\n\nMore from the book introduction: "We'll learn the core principles behind neural networks and deep learning by atta cking a concrete problem: the problem of teaching a computer to recognize handwritten digits. ...it can be solved pretty well using a simple neural network\, with just a few tens of lines of code\, and no special libraries ."\n\n"But you don't need to be a professional programmer."\n\nThe code pr ovided is in Python\, which even if you don't program in Python\, should b e easy to understand with just a little effort.\n\nBenefits of attending t he series:\n\n* Learn the core principles behind neural network and deep l earning.\n\n* See a simple Python program that solves a concrete problem: teaching a computer to recognize a handwritten digit.\n\n* Improve the res ult through incorporating more and more of core ideas about neural network s and deep learning.\n\n* Understand the theory\, with worked-out proofs o f fundamental equations of backpropagation for those interested.\n\n* Run straightforward Python demo code example.\n\nThe demo Python program (upda ted from version provided in the book) can be downloaded from the speaker' s GitHub account. The demo program is run in a Docker container that runs on your Mac\, Windows\, or Linux personal computer\; we plan to provide in structions on doing that in advance of the class.\n\n(That would be one go od reason to register early if you plan to attend\, in order that you can receive the straightforward instructions and leave yourself with plenty of time to prepare the Git and Docker software that are widely used among so ftware professionals.)\n\nDecision to (Run/Cancel) Date for this course is Tuesday\, June 15\, 2021\n\nSpeaker(s): CL Kim \, \n\nAgenda: \nAgenda:\n \nIntroduction to Practical Neural Networks and Deep Learning (Part 1)\nFe edforward Neural Networks.\n* Simple (Python) Network to classify a handwr itten digit\n* Learning with Gradient Descent\n* How the backpropagation a lgorithm works\n* Improving the way neural networks learn:\n** Cross-entro py cost function\n** Softmax activation function and log-likelihood cost f unction\n** Rectified Linear Unit\n** Overfitting and Regularization:\n*** L2 regularization\n*** Dropout\n*** Artificially expanding data set\n*** Hyper-parameters\n\nPre-requisites:\nThere is some heavier mathematics in proving the four fundamental equations behind backprogation\, so a basic f amiliarity with multivariable calculus and linear algebra is expected\, bu t nothing advanced is required. (The backpropagation equations can be also just accepted without bothering with the proofs since the provided python code for the simple network just makes use of the equations.)\n\nA live\, interactive webinar\, Boston\, Massachusetts\, United States\, Virtual: h ttps://events.vtools.ieee.org/m/270036 LOCATION:A live\, interactive webinar\, Boston\, Massachusetts\, United Sta tes\, Virtual: https://events.vtools.ieee.org/m/270036 ORGANIZER:ieeebostonsection@gmail.com SEQUENCE:9 SUMMARY:Introduction to Practical Neural Networks and Deep Learning (Part 1 ) URL;VALUE=URI:https://events.vtools.ieee.org/m/270036 X-ALT-DESC:Description: <br /><p><strong>Series Overview:</strong>&nbsp\; F rom the book introduction: "Neural networks and deep learning currently pr ovides the best solutions to many problems in image recognition\, speech r ecognition\, and natural language processing."</p>\n<p>This Part 1 and the planned Part 2 (winter or spring 2022\, to be confirmed) series of course s will teach many of the core concepts behind neural networks and deep lea rning.</p>\n<p><strong>More from the book introduction:</strong>&nbsp\; "W e'll learn the core principles behind neural networks and deep learning by attacking a concrete problem: the problem of teaching a computer to recog nize handwritten digits. ...it can be solved pretty well using a simple ne ural network\, with just a few tens of lines of code\, and no special libr aries."</p>\n<p>"But you don't need to be a professional programmer."</p>\ n<p>The code provided is in Python\, which even if you don't program in Py thon\, should be easy to understand with just a little effort.</p>\n<p><st rong>Benefits of attending the series:</strong></p>\n<p>* Learn the core p rinciples behind neural network and deep learning.</p>\n<p>* See a simple Python program that solves a concrete problem: teaching a computer to reco gnize a handwritten digit.</p>\n<p>* Improve the result through incorporat ing more and more of core ideas about neural networks and deep learning.</ p>\n<p>* Understand the theory\, with worked-out proofs of fundamental equ ations of backpropagation for those interested.</p>\n<p>* Run straightforw ard Python demo code example.</p>\n<p>The demo Python program (updated fro m version provided in the book) can be downloaded from the speaker's GitHu b account. The demo program is run in a Docker container that runs on your Mac\, Windows\, or Linux personal computer\; we plan to provide instructi ons on doing that in advance of the class.</p>\n<p><em>(That would be one good reason to register early if you plan to attend\, in order that you ca n receive the straightforward instructions and leave yourself with plenty of time to prepare the Git and Docker software that are widely used among software professionals.)</em></p>\n<p><em>Decision to (Run/Cancel) Date fo r this course is Tuesday\, June 15\, 2021</em></p><br /><br />Agenda: <br /><p>Agenda:</p>\n<p><br />Introduction to Practical Neural Networks and D eep Learning (Part 1)<br />Feedforward Neural Networks.<br />* Simple (Pyt hon) Network to classify a handwritten digit<br />* Learning with Gradient Descent<br />* How the backpropagation algorithm works<br />* Improving t he way neural networks learn:<br />** Cross-entropy cost function<br />** Softmax activation function and log-likelihood cost function<br />** Recti fied Linear Unit<br />** Overfitting and Regularization:<br />*** L2 regul arization<br />*** Dropout<br />*** Artificially expanding data set<br />* ** Hyper-parameters</p>\n<p>Pre-requisites:<br />There is some heavier mat hematics in proving the four fundamental equations behind backprogation\, so a basic familiarity with multivariable calculus and linear algebra is e xpected\, but nothing advanced is required. (The backpropagation equations can be also just accepted without bothering with the proofs since the pro vided python code for the simple network just makes use of the equations.) </p> END:VEVENT END:VCALENDAR