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:20241102T130108Z UID:C4891E10-9AC9-4F53-9D0C-E445EAB88078 DTSTART;TZID=US/Eastern:20241026T083000 DTEND;TZID=US/Eastern:20241026T123000 DESCRIPTION:THIS COURSE HAS BEEN CANCELLED!\n\nCourse 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 recognition\, speech recognition\, and natural language processing.”\n\nThis Part 1 and the planned Part 2 (to be confi rmed) series of courses will teach many of the core concepts behind neural networks and deep learning.\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 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 cl ass material is mostly from the highly-regarded and free online book “Ne ural Networks and Deep Learning” by Michael Nielsen\, plus additional ma terial such as some proofs of fundamental equations not provided in the bo ok.\n\nMore from the book introduction: Reference book: “Neural Networks and Deep Learning” by Michael Nielsen\, http://neuralnetworksanddeeplea rning.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 recognize handwritten digits. …it can be solved pretty well using a simple neural network\, with just a few tens of lines of code\, an d no special libraries.”\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 e ffort.\n\nBenefits of attending the series:\n\n* Learn the core principles behind neural networks and deep learning.\n* See a simple Python program that solves a concrete problem: teaching a computer to recognize a handwri tten 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 account. The demo program is run in a Docker container that runs o n your Mac\, Windows\, or Linux personal computer\; we plan to provide ins tructions on doing that in advance of the class.\n\n(That would be one goo d reason to register early if you plan to attend\, in order that you can r eceive the straightforward instructions and leave yourself with plenty of time to prepare the Git and Docker software that are widely used among sof tware professionals.)\n\nCourse Background and Content: This is a live ins tructor-led introductory course on Neural Networks and Deep Learning. It i s 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 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-regarded an d free online book “Neural Networks and Deep Learning” by Michael Niel sen\, plus additional material such as some proofs of fundamental equation s not provided in the book.\n\nOutline:\n\n- Feedforward Neural Networks\n - Simple (Python) Network to classify a handwritten digit\n- Learning with Stochastic Gradient Descent\n- How the backpropagation algorithm work\n- Improving the way neural networks learn:\n-\n- Cross-entropy cost function \n- SoftMax activation function and log-likelihood cost function\n- Rectif ied Linear Unit\n\n- Overfitting and Regularization:\n-\n- L2 regularizati on\n- Dropout\n- Artificially expanding data set\n\nPre-requisites: There is some heavier mathematics in learning the four fundamental equations beh ind backpropagation\, so a basic familiarity with multivariable calculus a nd matrix algebra is expected\, but nothing advanced is required. (The bac kpropagation equations can be also just accepted without bothering with th e proofs since the provided Python code for the simple network just make u se of the equations.) Basic familiarity with Python or similar computer la nguage.\n\nSpeaker(s): CL Kim\, \n\nBoston\, Massachusetts\, United States \, Virtual: https://events.vtools.ieee.org/m/414504 LOCATION:Boston\, Massachusetts\, United States\, Virtual: https://events.v tools.ieee.org/m/414504 ORGANIZER:k.safina@ieee.org SEQUENCE:16 SUMMARY:Introduction to Neural Networks and Deep Learning (Part I) - Cancel led! URL;VALUE=URI:https://events.vtools.ieee.org/m/414504 X-ALT-DESC:Description: <br /><p>THIS COURSE HAS BEEN CANCELLED!</p>\n<p>&n bsp\;</p>\n<p>Course Format:&nbsp\; &nbsp\;Live Webinar\, 4.0 hours of ins truction! Series Overview: &nbsp\; From the book introduction: &ldquo\;Neu ral networks and deep learning currently provides the best solutions to ma ny problems in image recognition\, speech recognition\, and natural langua ge processing.&rdquo\;<br><br>This Part 1 and the planned Part 2 (to be co nfirmed) series of courses will teach many of the core concepts behind neu ral networks and deep learning.</p>\n<p>This is a live instructor-led intr oductory 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 c overs a feedforward neural network (but not convolutional neural network i n 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 bo ok &ldquo\;Neural Networks and Deep Learning&rdquo\; by Michael Nielsen\, plus additional material such as some proofs of fundamental equations not provided in the book.<br><br>More from the book introduction: &nbsp\;Refer ence book: &ldquo\;Neural Networks and Deep Learning&rdquo\; by Michael Ni elsen\, <a href="http://neuralnetworksanddeeplearning.com/" target="_blank " rel="noopener" data-saferedirecturl="https://www.google.com/url?q=http:/ /neuralnetworksanddeeplearning.com/&amp\;source=gmail&amp\;ust=16687168717 80000&amp\;usg=AOvVaw2YFKDZOE9rV3h7YP9bcQcS">http://<wbr>neuralnetworksand deeplearning.<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 handwritten digits. &helli p\;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>&ld quo\;But you don&rsquo\;t need to be a professional programmer.&rdquo\;<br ><br>The code provided is in Python\, which even if you don&rsquo\;t progr am 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 progra m that solves a concrete problem: teaching a computer to recognize a handw ritten digit.<br>* Improve the result through incorporating more and more core ideas about neural networks and deep learning.<br>* Understand the th eory\, with worked-out proofs of fundamental&nbsp\;</p>\n<p>The demo Pytho n program (updated from version provided in the book) can be downloaded fr om the speaker&rsquo\;s GitHub account. The demo program is run in a Docke r container that runs on your Mac\, Windows\, 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 register early if you plan to atte nd\, in order that you can receive the straightforward instructions and le ave yourself with plenty of time to prepare the Git and Docker software th at are widely used among software professionals.)</p>\n<p>Course Backgroun d and Content: &nbsp\; This is a live instructor-led introductory course o n 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 feedforwa rd neural network (but not convolutional neural network in Part 1). It wil l be a pre-requisite for the planned Part 2 second course. The class mater ial is mostly from the highly-regarded and free online book &ldquo\;Neural Networks and Deep Learning&rdquo\; by Michael Nielsen\, plus additional m aterial such as some proofs of fundamental equations not provided in the b ook.</p>\n<p>Outline:</p>\n<ul>\n<li>Feedforward Neural Networks</li>\n<li >Simple (Python) Network to classify a handwritten digit</li>\n<li>Learnin g with Stochastic Gradient Descent</li>\n<li>How the backpropagation algor ithm 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 r egularization</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 mathem atics in learning the four fundamental equations behind backpropagation\, so a basic familiarity with multivariable calculus and matrix 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 make use of the equations.) Basic familiarity with Python or similar computer language.</p> END:VEVENT END:VCALENDAR