BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:US/Eastern BEGIN:DAYLIGHT DTSTART:20240310T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20241103T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20240319T134823Z UID:1B8C60A5-B6A4-4D30-8877-CBD361F84942 DTSTART;TZID=US/Eastern:20240316T090000 DTEND;TZID=US/Eastern:20240316T123000 DESCRIPTION:Course Format: Live Webinar\, 3.5 hours of instruction! Series Overview: From the book introduction: “Neural networks and deep learning currently provides the best solutions to many problems in image recogniti on\, speech recognition\, and natural language processing.”\n\nThis Part 1 and the planned Part 2\, (to be confirmed) series of courses will teach many of the core concepts behind neural networks and deep learning.\n\nTh is is a live instructor-led introductory course on Neural Networks and Dee p Learning. It is planned to be a two-part series of courses. The first co urse is complete by itself and covers a feedforward neural network (but no t convolutional neural network in Part 1). It will be a pre-requisite for the planned Part 2 second course. The class material is mostly from the hi ghly-regarded and free online book “Neural Networks and Deep Learning” by Michael Nielsen\, plus additional material such as some proofs of fund amental equations not provided in the book.\n\nMore from the book introduc tion: Reference book: “Neural Networks and Deep Learning” by Michael N ielsen\, http://neuralnetworksanddeeplearning.com/ “We’ll learn the co re principles behind neural networks and deep learning by attacking a conc rete problem: the problem of teaching a computer to recognize handwritten digits. …it can be solved pretty well using a simple neural network\, wi th just a few tens of lines of code\, and no special libraries.”\n\n“B ut you don’t need to be a professional programmer.”\n\nThe code provid ed is in Python\, which even if you don’t program in Python\, should be easy to understand with just a little effort.\n\nBenefits of attending the series:\n\n* Learn the core principles behind neural networks and deep le arning.\n* See a simple Python program that solves a concrete problem: tea ching a computer to recognize a handwritten digit.\n* Improve the result t hrough incorporating more and more core ideas about neural networks and de ep learning.\n* Understand the theory\, with worked-out proofs of fundamen tal\n\nThe demo Python program (updated from version provided in the book) can be downloaded from the speaker’s GitHub account. The demo program i s run in a Docker container that runs on your Mac\, Windows\, or Linux per sonal computer\; we plan to provide instructions on doing that in advance of the class.\n\n(That would be one good reason to register early if you p lan to attend\, in order that you can receive the straightforward instruct ions and leave yourself with plenty of time to prepare the Git and Docker software that are widely used among software professionals.)\n\nCourse Bac kground and Content: This is a live instructor-led introductory course on Neural Networks and Deep Learning. It is planned to be a two-part series o f courses. The first course is complete by itself and covers a feedforward neural network (but not convolutional neural network in Part 1). It will be a pre-requisite for the planned Part 2 second course. The class materia l is mostly from the highly-regarded and free online book “Neural Networ ks and Deep Learning” by Michael Nielsen\, plus additional material such as some proofs of fundamental equations not provided in the book.\n\nOutl ine:\n\n- Feedforward Neural Networks\n- Simple (Python) Network to classi fy a handwritten digit\n- Learning with Stochastic Gradient Descent\n- How the backpropagation algorithm work\n- Improving the way neural networks l earn:\n-\n- Cross-entropy cost function\n- SoftMax activation function and log-likelihood cost function\n- Rectified Linear Unit\n\n- Overfitting an d Regularization:\n-\n- L2 regularization\n- Dropout\n- Artificially expan ding data set\n\nPre-requisites: There is some heavier mathematics in lear ning the four fundamental equations behind backpropagation\, so a basic fa miliarity with multivariable calculus and matrix algebra is expected\, but 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 make use of the equations.) Basic familia rity with Python or similar computer language.\n\nSpeaker(s): CL Kim\, \n\ nBoston\, Massachusetts\, United States\, Virtual: https://events.vtools.i eee.org/m/401136 LOCATION:Boston\, Massachusetts\, United States\, Virtual: https://events.v tools.ieee.org/m/401136 ORGANIZER:k.safina@ieee.org SEQUENCE:21 SUMMARY:Introduction to Neural Networks and Deep Learning (Part I) URL;VALUE=URI:https://events.vtools.ieee.org/m/401136 X-ALT-DESC:Description: <br /><p>Course Format:&nbsp\; &nbsp\;Live Webinar\ , 3.5 hours of instruction! Series Overview: &nbsp\; From the book introdu ction: &ldquo\;Neural networks and deep learning currently provides the be st solutions to many problems in image recognition\, speech recognition\, and natural language processing.&rdquo\;<br><br>This Part 1 and the planne d Part 2\, (to be confirmed) series of courses will teach many of the core concepts behind neural networks and deep learning.</p>\n<p>This is a live instructor-led introductory course on Neural Networks and Deep Learning. It is planned to be a two-part series of courses. The first course is comp lete by itself and covers a feedforward neural network (but not convolutio nal neural network in Part 1). It will be a pre-requisite for the planned Part 2 second course. The class material is mostly from the highly-regarde d and free online book &ldquo\;Neural Networks and Deep Learning&rdquo\; b y Michael Nielsen\, plus additional material such as some proofs of fundam ental equations not provided in the book.<br><br>More from the book introd uction: &nbsp\;Reference book: &ldquo\;Neural Networks and Deep Learning&r dquo\; by Michael Nielsen\, <a href="http://neuralnetworksanddeeplearning. com/" target="_blank" rel="noopener" data-saferedirecturl="https://www.goo gle.com/url?q=http://neuralnetworksanddeeplearning.com/&amp\;source=gmail& amp\;ust=1668716871780000&amp\;usg=AOvVaw2YFKDZOE9rV3h7YP9bcQcS">http://<w br>neuralnetworksanddeeplearning.<wbr>com/</a> &ldquo\;We&rsquo\;ll learn the core principles behind neural networks and deep learning by attacking a concrete problem: the problem of teaching a computer to recognize handwr itten digits. &hellip\;it can be solved pretty well using a simple neural network\, with just a few tens of lines of code\, and no special libraries .&rdquo\;<br><br>&ldquo\;But you don&rsquo\;t need to be a professional pr ogrammer.&rdquo\;<br><br>The code provided is in Python\, which even if yo u don&rsquo\;t program in Python\, should be easy to understand with just a little effort.</p>\n<p>Benefits of attending the series:</p>\n<p>* Learn the core principles behind neural networks and deep learning.<br>* See a simple Python program that solves a concrete problem: teaching a computer to recognize a handwritten digit.<br>* Improve the result through incorpor ating more and more core ideas about neural networks and deep learning.<br >* Understand the theory\, with worked-out proofs of fundamental&nbsp\;</p >\n<p>The demo Python program (updated from version provided in the book) can be downloaded from the speaker&rsquo\;s GitHub account. The demo progr am is run in a Docker container that runs on your Mac\, Windows\, or Linux personal computer\; we plan to provide instructions on doing that in adva nce of the class.</p>\n<p>(That would be one good 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 an d Docker software that are widely used among software professionals.)</p>\ n<p>Course Background and Content: &nbsp\; This is a live instructor-led i ntroductory course on Neural Networks and Deep Learning. It is planned to be a two-part series of courses. The first course is complete by itself an d covers a feedforward neural network (but not convolutional neural networ k in Part 1). It will be a pre-requisite for the planned Part 2 second cou rse. The class material is mostly from the highly-regarded and free online book &ldquo\;Neural Networks and Deep Learning&rdquo\; by Michael Nielsen \, plus additional material such as some proofs of fundamental equations n ot provided in the book.</p>\n<p>Outline:</p>\n<ul>\n<li>Feedforward Neura l Networks</li>\n<li>Simple (Python) Network to classify a handwritten dig it</li>\n<li>Learning with Stochastic Gradient Descent</li>\n<li>How the b ackpropagation algorithm work</li>\n<li>Improving the way neural networks learn:</li>\n<li>\n<ul>\n<li>Cross-entropy cost function</li>\n<li>SoftMax activation function and log-likelihood cost function</li>\n<li>Rectified Linear Unit</li>\n</ul>\n</li>\n<li>Overfitting and Regularization:</li>\n <li>\n<ul>\n<li>L2 regularization</li>\n<li>Dropout</li>\n<li>Artificially expanding data set</li>\n</ul>\n</li>\n</ul>\n<p>Pre-requisites: There is some heavier mathematics in learning the four fundamental equations behin d backpropagation\, so a basic familiarity with multivariable calculus and matrix algebra is expected\, but nothing advanced is required. (The backp ropagation equations can be also just accepted without bothering with the proofs since the provided Python code for the simple network just make use of the equations.) Basic familiarity with Python or similar computer lang uage.</p> END:VEVENT END:VCALENDAR