BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Asia/Kolkata
BEGIN:STANDARD
DTSTART:19451014T230000
TZOFFSETFROM:+0630
TZOFFSETTO:+0530
TZNAME:IST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20211225T120117Z
UID:760E045F-12B1-4B12-B8D2-00B53B3224DE
DTSTART;TZID=Asia/Kolkata:20211217T180000
DTEND;TZID=Asia/Kolkata:20211217T190000
DESCRIPTION:CIS Chapter\, IEEE UP Section (CIS11) organized a Lecture Serie
 s on "Computational Intelligence". The speaker of the lecture was Dr. Nish
 chal K. Verma\, Professor in the Dept. of Electrical Engineering at the In
 dian Institute of Technology Kanpur\, India.\n\nSpeaker(s): Nishchal K. Ve
 rma\, \n\nAgenda: \nAbstract of the talk:\n\nWe are living in an era where
  Artificial Intelligence (AI) has started to scratch the surface of its tr
 ue potential. Not only does AI create the possibility of disrupting indust
 ries and transforming the workplace\, but it can also address some of soci
 ety’s biggest challenges. Autonomous vehicles may save tens of thousands
  of lives and increase mobility for the elderly and the disabled. Precisio
 n medicine may unlock tailored individual treatment that extends life. Sma
 rt buildings may help reduce carbon emissions and save energy. These are j
 ust a few of the potential benefits that AI promises\, and is starting to 
 deliver upon. Even with the advances and success of deep learning algorith
 ms in various applications like speech recognition\, image classification\
 , handwriting recognition\, fraud detection\, etc.\, the deep learning mod
 el has still some limitations. Due to advancements in fuzzy logic and syst
 ems in the past decades\, handling such complex data has become easy. In e
 ffect\, the addition of fuzziness into the model of a neuron makes it bett
 er to adapt the behavior of underlying systems that are imprecisely define
 d through their high degree of complexity. The linguistic and numeric form
 s of data can be handled together by a Deep Fuzzy Network (DFN). DFN is de
 veloped using both Mamdani and Takagi-Sugeno FIS where nodes of hidden lay
 ers act as Mamdani or Takagi-Sugeno FIS. DFN has high robustness towards u
 ncertainties due to vagueness\, imprecision\, and ambiguity. There is a wi
 de scope to develop very effective machine learning architectures based on
  DFNs with high abstraction quality\, high robustness towards uncertainty 
 due to vagueness\, ambiguity\, and imprecision as well as uncertainty due 
 to randomness and intuitively intelligible to human beings in terms of des
 ign and working.\n\nKanpur\, Uttar Pradesh\, India\, 208016\, Virtual: htt
 ps://events.vtools.ieee.org/m/296673
LOCATION:Kanpur\, Uttar Pradesh\, India\, 208016\, Virtual: https://events.
 vtools.ieee.org/m/296673
ORGANIZER:vrij@iiita.ac.in
SEQUENCE:1
SUMMARY:Expert Lecture on "Deep Learning and Artificial Intelligence"
URL;VALUE=URI:https://events.vtools.ieee.org/m/296673
X-ALT-DESC:Description: <br /><p>CIS Chapter\, IEEE UP Section (CIS11) orga
 nized a Lecture Series on "Computational Intelligence". The speaker of the
  lecture was Dr. Nishchal K. Verma\, Professor in the Dept. of Electrical 
 Engineering at the Indian Institute of Technology Kanpur\, India.</p><br /
 ><br />Agenda: <br /><h4><strong>Abstract of the talk:</strong></h4>\n<p a
 lign="justify">We are living in an era where Artificial Intelligence (AI) 
 has started to scratch the surface of its true potential. Not only does AI
  create the possibility of disrupting industries and transforming the work
 place\, but it can also address some of society&rsquo\;s biggest challenge
 s. Autonomous vehicles may save tens of thousands of lives and increase mo
 bility for the elderly and the disabled. Precision medicine may unlock tai
 lored individual treatment that extends life. Smart buildings may help red
 uce carbon emissions and save energy. These are just a few of the potentia
 l benefits that AI promises\, and is starting to deliver upon. Even with t
 he advances and success of deep learning algorithms in various application
 s like speech recognition\, image classification\, handwriting recognition
 \, fraud detection\, etc.\, the deep learning model has still some limitat
 ions. Due to advancements in fuzzy logic and systems in the past decades\,
  handling such complex data has become easy. In effect\, the addition of f
 uzziness into the model of a neuron makes it better to adapt the behavior 
 of underlying systems that are imprecisely defined through their high degr
 ee of complexity. The linguistic and numeric forms of data can be handled 
 together by a Deep Fuzzy Network (DFN). DFN is developed using both Mamdan
 i and Takagi-Sugeno FIS where nodes of hidden layers act as Mamdani or Tak
 agi-Sugeno FIS. DFN has high robustness towards uncertainties due to vague
 ness\, imprecision\, and ambiguity. There is a wide scope to develop very 
 effective machine learning architectures based on DFNs with high abstracti
 on quality\, high robustness towards uncertainty due to vagueness\, ambigu
 ity\, and imprecision as well as uncertainty due to randomness and intuiti
 vely intelligible to human beings in terms of design and working.</p>
END:VEVENT
END:VCALENDAR