BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:US/Eastern
BEGIN:DAYLIGHT
DTSTART:20220313T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20221106T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20220324T152453Z
UID:353D918A-22FF-4F92-B188-ED3DBE781628
DTSTART;TZID=US/Eastern:20220319T090000
DTEND;TZID=US/Eastern:20220319T120000
DESCRIPTION:Series Overview: From the book introduction: &quot;Neural networks a
 nd deep learning currently provides the best solutions to many problems in
  image recognition\, speech recognition\, and natural language processing.
 &quot;\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: &quot;We&#39;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
 .&quot;\n\n&quot;But you don&#39;t need to be a professional programmer.&quot;\n\nThe code pr
 ovided is in Python\, which even if you don&#39;t program in Python\, should b
 e easy to understand with just a little effort.\n\nPre-requisites: There i
 s some heavier mathematics in learning the four fundamental equations behi
 nd backpropagation\, so a basic familiarity with multivariable calculus an
 d matrix algebra is expected\, but nothing advanced is required. (The back
 propagation equations can be also just accepted without bothering with the
  proofs since the provided Python code for the simple network just make us
 e of the equations.) Basic familiarity with Python or similar computer lan
 guage.\n\nBenefits of attending the series:\n\n* Learn the core principles
  behind neural networks and deep learning.\n\n* See a simple Python progra
 m that solves a concrete problem: teaching a computer to recognize a handw
 ritten digit.\n\n* Improve the result through incorporating more and more 
 core ideas about neural networks and deep learning.\n\n* Understand the th
 eory\, with worked-out proofs of fundamental equations of backpropagation 
 for those interested.\n\n* Run straightforward Python demo code example.\n
 \nThe demo Python program (updated from version provided in the book) can 
 be downloaded from the speaker&#39;s GitHub account. The demo program is run i
 n a Docker container that runs on your Mac\, Windows\, or Linux personal c
 omputer\; 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 plan to 
 attend\, in order that you can receive the straightforward instructions an
 d leave yourself with plenty of time to prepare the Git and Docker softwar
 e that are widely used among software professionals.)\n\nCourse Background
  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 of cours
 es. 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 pr
 e-requisite for the planned Part 2 second course. The class material is mo
 stly from the highly-regarded and free online book &quot;Neural Networks and De
 ep Learning&quot; by Michael Nielsen\, plus additional material such as some pr
 oofs of fundamental equations not provided in the book.\n\nSpeaker(s): CL 
 Kim\, \n\nBoston\, Massachusetts\, United States\, Virtual: https://events
 .vtools.ieee.org/m/289782
LOCATION:Boston\, Massachusetts\, United States\, Virtual: https://events.v
 tools.ieee.org/m/289782
ORGANIZER:k.safina@ieee.org
SEQUENCE:6
SUMMARY:Introduction to Practical Neural Networks and Deep Learning (Part I
 ) Course 
URL;VALUE=URI:https://events.vtools.ieee.org/m/289782
X-ALT-DESC:Description: &lt;br /&gt;&lt;p&gt;&lt;strong&gt;Series Overview:&lt;/strong&gt;&amp;nbsp\; &amp;
 nbsp\;From the book introduction: &quot;Neural networks and deep learning curre
 ntly provides the best solutions to many problems in image recognition\, s
 peech recognition\, and natural language processing.&quot;&lt;/p&gt;\n&lt;p&gt;This Part 1 
 and the planned Part 2 (winter or spring 2022\, to be confirmed) series of
  courses will teach many of the core concepts behind neural networks and d
 eep learning.&lt;/p&gt;\n&lt;p&gt;&lt;strong&gt;More from the book introduction:&lt;/strong&gt;&amp;nb
 sp\; &quot;We&#39;ll learn the core principles behind neural networks and deep lear
 ning by attacking a concrete problem: the problem of teaching a computer t
 o recognize handwritten digits. ...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.&quot;&lt;/p&gt;\n&lt;p&gt;&quot;But you don&#39;t need to be a professional programmer
 .&quot;&lt;/p&gt;\n&lt;p&gt;The code provided is in Python\, which even if you don&#39;t progra
 m in Python\, should be easy to understand with just a little effort.&lt;/p&gt;\
 n&lt;p&gt;&lt;strong&gt;Pre-requisites:&lt;/strong&gt; There is some heavier mathematics in 
 learning the four fundamental equations behind backpropagation\, so a basi
 c familiarity with multivariable calculus and matrix algebra is expected\,
  but nothing advanced is required. (The backpropagation equations can be a
 lso just accepted without bothering with the proofs since the provided Pyt
 hon code for the simple network just make use of the equations.) Basic fam
 iliarity with Python or similar computer language.&lt;/p&gt;\n&lt;p&gt;&lt;strong&gt;Benefit
 s of attending the series:&lt;/strong&gt;&lt;/p&gt;\n&lt;p&gt;* Learn the core principles be
 hind neural networks and deep learning.&lt;/p&gt;\n&lt;p&gt;* See a simple Python prog
 ram that solves a concrete problem: teaching a computer to recognize a han
 dwritten digit.&lt;/p&gt;\n&lt;p&gt;* Improve the result through incorporating more an
 d more core ideas about neural networks and deep learning.&lt;/p&gt;\n&lt;p&gt;* Under
 stand the theory\, with worked-out proofs of fundamental equations of back
 propagation for those interested.&lt;/p&gt;\n&lt;p&gt;* Run straightforward Python dem
 o code example.&lt;/p&gt;\n&lt;p&gt;The demo Python program (updated from version prov
 ided in the book) can be downloaded from the speaker&#39;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 instructions on doing t
 hat in advance of the class.&lt;/p&gt;\n&lt;p&gt;&lt;em&gt;(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 pre
 pare the Git and Docker software that are widely used among software profe
 ssionals.)&lt;/em&gt;&lt;/p&gt;\n&lt;p&gt;&lt;strong&gt;Course Background and Content:&lt;/strong&gt;&amp;nb
 sp\; &amp;nbsp\;This is a live instructor-led introductory course on Neural Ne
 tworks 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 n
 etwork (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 most
 ly from the highly-regarded and free online book &quot;Neural Networks and Deep
  Learning&quot; by Michael Nielsen\, plus &lt;strong&gt;additional material such as s
 ome proofs of fundamental equations not provided in the book.&lt;/strong&gt;&lt;/p&gt;
END:VEVENT
END:VCALENDAR