BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:US/Eastern BEGIN:DAYLIGHT DTSTART:20250309T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20251102T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20250325T144102Z UID:AA65D123-07DE-4901-A0B4-7B5D7DCFA153 DTSTART;TZID=US/Eastern:20250322T083000 DTEND;TZID=US/Eastern:20250322T123000 DESCRIPTION:Course Format: Live Webinar\, 4.0 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\nRegistrat ion Fees:\n\nMembers Early Rate: $115.00\n\nMembers Rate after (March 7th) : $130.00\n\nNon-Member Early Rate: $135.00\n\nNon-Member Rate after(March 7th): $150.00\n\nDecision to run or cancel the course is: Friday\, March 14\, 2025\n\nThis Part 1 and the planned Part 2 (to be confirmed) series o f courses will teach many of the core concepts behind neural networks and deep learning.\n\nThis is a live instructor-led introductory course on Neu ral Networks and Deep Learning. It is planned to be a two-part series of c ourses. The first course is complete by itself and covers a feedforward ne ural network (but not convolutional neural network in Part 1). It will be a pre-requisite for the planned Part 2 second course. The class material i s mostly from the highly-regarded and free online book “Neural Networks and Deep Learning” by Michael Nielsen\, plus additional material such as some proofs of fundamental equations not provided in the book.\n\nMore fr om the book introduction: Reference book: “Neural Networks and Deep Lear ning” by Michael Nielsen\, http://neuralnetworksanddeeplearning.com/ “ We’ll learn the core principles behind neural networks and deep learning by attacking a concrete problem: the problem of teaching a computer to re cognize 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 l ibraries.”\n\n“But you don’t need to be a professional programmer. ”\n\nThe code provided is in Python\, which even if you don’t program in Python\, should be easy to understand with just a little effort.\n\nBen efits of attending the series:\n\n* Learn the core principles behind neura l networks and deep learning.\n* See a simple Python program that solves a concrete problem: teaching a computer to recognize a handwritten digit.\n * Improve the result through incorporating more and more core ideas about neural networks and deep learning.\n* Understand the theory\, with worked- out proofs of fundamental\n\nThe demo Python program (updated from version provided in the book) can be downloaded from the speaker’s GitHub accou nt. The demo program 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 advance of the class.\n\n(That would be one good reason to r egister early if you plan to attend\, in order that you can receive the st raightforward instructions and leave yourself with plenty of time to prepa re the Git and Docker software that are widely used among software profess ionals.)\n\nCourse Background and Content: 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 “Neural Networks and Deep Learning” by Michael Nielsen\, plus ad ditional material such as some proofs of fundamental equations not provide d in the book.\n\nOutline:\n\n- Feedforward Neural Networks\n- Simple (Pyt hon) Network to classify a handwritten digit\n- Learning with Stochastic G radient Descent\n- How the backpropagation algorithm work\n- Improving the way neural networks learn:\n-\n- Cross-entropy cost function\n- SoftMax a ctivation function and log-likelihood cost function\n- Rectified Linear Un it\n\n- Overfitting and Regularization:\n-\n- L2 regularization\n- Dropout \n- Artificially expanding data set\n\nPre-requisites: There is some heavi er mathematics in learning the four fundamental equations behind backpropa gation\, so a basic familiarity with multivariable calculus and matrix alg ebra is expected\, but nothing advanced is required. (The backpropagation equations can be also just accepted without bothering with the proofs sinc e the provided Python code for the simple network just make use of the equ ations.) Basic familiarity with Python or similar computer language.\n\nSp eaker(s): CL Kim\, \n\nBoston\, Massachusetts\, United States\, Virtual: h ttps://events.vtools.ieee.org/m/450631 LOCATION:Boston\, Massachusetts\, United States\, Virtual: https://events.v tools.ieee.org/m/450631 ORGANIZER:k.safina@ieee.org SEQUENCE:19 SUMMARY:Introduction to Neural Networks and Deep Learning (Part I) URL;VALUE=URI:https://events.vtools.ieee.org/m/450631 X-ALT-DESC:Description: <br /><p>Course Format:&nbsp\; &nbsp\;Live Webinar\ , 4.0 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\;</p>\n<p>Registration Fees:</p>\n< p>Members Early Rate:&nbsp\; $115.00</p>\n<p>Members Rate after (March 7th ):&nbsp\; $130.00</p>\n<p>Non-Member Early Rate:&nbsp\; $135.00</p>\n<p>No n-Member Rate after(March 7th):&nbsp\; $150.00</p>\n<p>Decision to run or cancel the course is:&nbsp\; Friday\, March 14\, 2025</p>\n<p>This 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.</p>\n<p>Th 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 &ldquo\;Neural Networks and Deep Learni ng&rdquo\; by Michael Nielsen\, plus additional material such as some proo fs of fundamental equations not provided in the book.<br><br>More from the book introduction: &nbsp\;Reference book: &ldquo\;Neural Networks and Dee p Learning&rdquo\; by Michael Nielsen\, <a href="http://neuralnetworksandd eeplearning.com/" target="_blank" rel="noopener" data-saferedirecturl="htt ps://www.google.com/url?q=http://neuralnetworksanddeeplearning.com/&amp\;s ource=gmail&amp\;ust=1668716871780000&amp\;usg=AOvVaw2YFKDZOE9rV3h7YP9bcQc S">http://<wbr>neuralnetworksanddeeplearning.<wbr>com/</a> &ldquo\;We&rsqu o\;ll learn the core principles behind neural networks and deep learning b y attacking a concrete problem: the problem of teaching a computer to reco gnize handwritten digits. &hellip\;it can be solved pretty well using a si mple neural network\, with just a few tens of lines of code\, and no speci al libraries.&rdquo\;<br><br>&ldquo\;But you don&rsquo\;t need to be a pro fessional programmer.&rdquo\;<br><br>The code provided is in Python\, whic h even if you don&rsquo\;t program in Python\, should be easy to understan d 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 thro ugh incorporating more and more core ideas about neural networks and deep learning.<br>* Understand the theory\, with worked-out proofs of fundament al&nbsp\;</p>\n<p>The demo Python program (updated from version provided i n the book) can be downloaded from the speaker&rsquo\;s GitHub account. Th e demo program is run in a Docker container that runs on your Mac\, Window s\, or Linux personal computer\; we plan to provide instructions on doing that in advance of the class.</p>\n<p>(That would be one good reason to re gister early if you plan to attend\, in order that you can receive the str aightforward instructions and leave yourself with plenty of time to prepar e the Git and Docker software that are widely used among software professi onals.)</p>\n<p>Course Background and Content: &nbsp\; This is a live inst ructor-led introductory 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 and covers a feedforward neural network (but not convolutional n eural 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-regarded and free online book &ldquo\;Neural Networks and Deep Learning&rdquo\; by Mic hael Nielsen\, plus additional material such as some proofs of fundamental equations not provided in the book.</p>\n<p>Outline:</p>\n<ul>\n<li>Feedf orward Neural Networks</li>\n<li>Simple (Python) Network to classify a han dwritten digit</li>\n<li>Learning with Stochastic Gradient Descent</li>\n< li>How the backpropagation algorithm work</li>\n<li>Improving the way neur al 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<l i>Rectified Linear Unit</li>\n</ul>\n</li>\n<li>Overfitting and Regulariza tion:</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-requisit es: There is some heavier mathematics in learning the four fundamental equ ations behind backpropagation\, so a basic familiarity with multivariable calculus and matrix algebra is expected\, but nothing advanced is required . (The backpropagation equations can be also just accepted without botheri ng with the proofs since the provided Python code for the simple network j ust make use of the equations.) Basic familiarity with Python or similar c omputer language.</p> END:VEVENT END:VCALENDAR