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:20210524T142811Z UID:BBDC3C0D-8170-4FCE-B998-BBA70EB5AE54 DTSTART;TZID=US/Eastern:20210320T090000 DTEND;TZID=US/Eastern:20210320T121500 DESCRIPTION:This course is confirmed to run on Saturday\, March 20th!\n\nCo urse Background and Content:\n\nThis is a live instructor-led introductory course on Neural Networks and Deep Learning. It is planned to be a two-pa rt series of courses. The first course is complete by itself. It will be a pre-requisite for the planned second course. The class material is mostly from the highly-regarded and free online book “Neural Networks and Deep Learning” by Michael Nielsen\, plus additional material such as some pr oofs of fundamental equations not provided in the book\, and (in planned P art 2) touching on more recent neural network types such as ResNet.\n\n3 h ours of instruction!\n\nFrom the book introduction: “Neural networks and deep learning currently provides the best solutions to many problems in i mage recognition\, speech recognition\, and natural language processing. ”\n\nThis Part 1 and the planned Part 2 (late spring/early summer 2021\, to be confirmed) series of courses will teach many of the core concepts b ehind neural networks and deep learning.\n\nReference book:\n\n“Neural N etworks and Deep Learning” by Michael Nielsen\, [http://neuralnetworksan ddeeplearning.com](http://neuralnetworksanddeeplearning.com/)\nMore from t he book introduction: “We’ll learn the core principles behind neural n etworks and deep learning by attacking a concrete problem: the problem of teaching a computer to recognize handwritten digits. ...it can be solved p retty well using a simple neural network\, with just a few tens of lines o f code\, and no special libraries.” “But you don’t need to be a prof essional 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 l ittle effort.\n\nBenefits of attending the series:\n\n* Learn the core pri nciples behind neural networks and deep learning.\n* See a simple python p rogram that solves a concrete problem: teaching a computer to recognize a handwritten digit.\n* Improve the result through incorporating more and mo re of core ideas about neural networks and deep learning.\n* Principle-ori ented\, with worked-out proofs of fundamental equations of backpropagation for those interested.\n* Yet hands-on practical\, with simple code exampl es.\n\nSpeaker(s): CL Kim \, \n\nAgenda: \nAgenda:\n\nIntroduction to Prac tical Neural Networks and Deep Learning (Part 1)\nFeedforward Neural Netwo rks.\n* Simple (Python) Network to classify a handwritten digit\n* Learnin g with Gradient Descent\n* How the backpropagation algorithm works\n* Impr oving the way neural networks learn:\n** Cross-entropy cost function\n** S oftmax activation function and log-likelihood cost function\n** Rectified Linear Unit\n** Overfitting and Regularization:\n*** L2 regularization\n** * Dropout\n*** Artificially expanding data set\n*** Hyper-parameters\n\nPr e-requisites:\nThere is some heavier mathematics in proving the four funda mental equations behind backprogation\, so a basic familiarity with multiv ariable calculus and linear 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 n etwork just makes use of the equations.)\n\nA live\, interactive webinar\, Boston\, Massachusetts\, United States\, Virtual: https://events.vtools.i eee.org/m/253675 LOCATION:A live\, interactive webinar\, Boston\, Massachusetts\, United Sta tes\, Virtual: https://events.vtools.ieee.org/m/253675 ORGANIZER:ieeebostonsection@gmail.com SEQUENCE:13 SUMMARY:Introduction to Practical Neural Networks and Deep Learning (Part 1 ) URL;VALUE=URI:https://events.vtools.ieee.org/m/253675 X-ALT-DESC:Description: <br /><p>This course is confirmed to run on Saturda y\, March 20th!&nbsp\;</p>\n<p>Course Background and Content:</p>\n<p><br />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 firs t course is complete by itself. It will be a pre-requisite for the planned second course. The class material is mostly from the highly-regarded and free online book &ldquo\;Neural Networks and Deep Learning&rdquo\; by Mich ael Nielsen\, plus additional material such as some proofs of fundamental equations not provided in the book\, and (in planned Part 2) touching on m ore recent neural network types such as ResNet.</p>\n<p>3 hours of instruc tion!</p>\n<p>From the book introduction: &ldquo\;Neural networks and deep learning currently provides the best solutions to many problems in image recognition\, speech recognition\, and natural language processing.&rdquo\ ;<br /><br />This Part 1 and the planned Part 2 (late spring/early summer 2021\, to be confirmed) series of courses will teach many of the core conc epts behind neural networks and deep learning.<br /><br />Reference book:< /p>\n<p><br />&ldquo\;Neural Networks and Deep Learning&rdquo\; by Michael Nielsen\,&nbsp\;<a href="http://neuralnetworksanddeeplearning.com/" targe t="_blank" rel="noopener" data-saferedirecturl="https://www.google.com/url ?q=http://neuralnetworksanddeeplearning.com&amp\;source=gmail&amp\;ust=160 9337576863000&amp\;usg=AFQjCNGgbg2vqyLTqa1OzIHqE7V851xkng">http://<wbr />n euralnetworksanddeeplearning.<wbr />com</a><br />More from the book introd uction: &ldquo\;We&rsquo\;ll learn the core principles behind neural netwo rks and deep learning by attacking a concrete problem: the problem of teac hing a computer to recognize handwritten digits. ...it can be solved prett y well using a simple neural network\, with just a few tens of lines of co de\, and no special libraries.&rdquo\; &ldquo\;But you don&rsquo\;t need t o be a professional programmer.&rdquo\;</p>\n<p><br />The code provided is in Python\, which even if you don&rsquo\;t program in Python\, should be easy to understand with just a little effort.<br /><br />Benefits of atten ding the series:</p>\n<p><br />* Learn the core principles behind neural n etworks 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 incorporating more and more of core idea s about neural networks and deep learning.<br />* Principle-oriented\, wit h worked-out proofs of fundamental equations of backpropagation for those interested.<br />* Yet hands-on practical\, with simple code examples.</p> <br /><br />Agenda: <br /><p>Agenda:</p>\n<p><br />Introduction to Practic al Neural Networks and Deep Learning (Part 1)<br />Feedforward Neural Netw orks.<br />* Simple (Python) Network to classify a handwritten digit<br /> * Learning with Gradient Descent<br />* How the backpropagation algorithm works<br />* Improving the way neural networks learn:<br />** Cross-entrop y cost function<br />** Softmax activation function and log-likelihood cos t function<br />** Rectified Linear Unit<br />** Overfitting and Regulariz ation:<br />*** L2 regularization<br />*** Dropout<br />*** Artificially e xpanding data set<br />*** Hyper-parameters</p>\n<p>Pre-requisites:<br />T here is some heavier mathematics in proving the four fundamental equations behind backprogation\, so a basic familiarity with multivariable calculus and linear algebra is expected\, but nothing advanced is required. (The b ackpropagation equations can be also just accepted without bothering with the proofs since the provided python code for the simple network just make s use of the equations.)</p> END:VEVENT END:VCALENDAR