BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
BEGIN:DAYLIGHT
DTSTART:20221002T030000
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=10
TZNAME:AEDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20230402T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=4
TZNAME:AEST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230818T154057Z
UID:494C4E51-26EA-4F69-B557-0D663326430F
DTSTART;TZID=Australia/Melbourne:20230303T100000
DTEND;TZID=Australia/Melbourne:20230303T110000
DESCRIPTION:Topic: Integrating Explainability into Machine Learning Models\
 nSpeaker: Dr. Zahid Islam\, CSIRO\n\nDate/Time: 10-11am\, Friday 3/3/2023\
 nVenue: Online via MS Teams. A link will be emailed prior to the seminar.\
 n\nRSVP: https://www.meetup.com/en-AU/canberradatasci/events/291927245/\n\
 nAbstract: Machine learning is everywhere. One of the fundamental goals of
  developing machine learning models is to reduce loss (measured by some fu
 nction) and increase accuracy (measure by comparing predictions and ground
  truth). Often high performing machine learning models are complex Deep Ne
 ural Network which performs numerical computation based on inputs and many
  parameters. Loss and accuracy metrices drive the computations in the netw
 ork. However\, the metrices are not indicative of the actual reasoning per
 formed internally by the models. High performing model can erroneously giv
 e good predictions by incorrect reasoning. In this talk I will discuss how
  explainability can help build reliable machine learning models in practic
 e.\n\nBio: I am a post-doctoral fellow in the Conservation Decisions Team 
 of CSIRO&#39;s Environment business unit. I am in the Machine Learning and Art
 ificial Intelligence (MLAI) FSP. My interest is in the pragmatic applicati
 ons of MLAI. My research is focused on Explainable Artificial Intelligence
  (XAI). I have been trying to explain complex time series models developed
  using deep neural networks and graph neural networks to humans. In doing 
 so\, I have been exploring any latent relationships between features and t
 argets.\n\nI obtained a PhD in Information Sciences from the University of
  South Australia. Within my PhD\, I developed ensemble methods for text cl
 assification incorporating XAI. I have also completed an MSc in Computer S
 cience from St Francis Xavier University\, Canada. As part of my MSc\, I d
 eveloped a framework for healthcare workflow verification using Computatio
 n Tree Logic (CTL). I have obtained a BSc in Computer Science and Engineer
 ing from Khulna University\, Bangladesh. In between studies\, I have worke
 d as part of the teaching faculty at Khulna University\, Bangladesh and as
  a software engineer at different organizations.\n\nCanberra\, Australian 
 Capital Territory\, Australia
LOCATION:Canberra\, Australian Capital Territory\, Australia
ORGANIZER:yanchang.zhao@csiro.au
SEQUENCE:2
SUMMARY:Integrating Explainability into Machine Learning Models
URL;VALUE=URI:https://events.vtools.ieee.org/m/350613
X-ALT-DESC:Description: &lt;br /&gt;&lt;p class=&quot;m_3725849889302545826mb-4&quot;&gt;&lt;strong&gt;
 &lt;span data-originalfontsize=&quot;12pt&quot; data-originalcomputedfontsize=&quot;16&quot;&gt;Topi
 c:&lt;/span&gt;&lt;/strong&gt;&lt;span class=&quot;m_3725849889302545826apple-converted-space&quot;
 &gt;&amp;nbsp\;&lt;/span&gt;&lt;span data-originalfontsize=&quot;12pt&quot; data-originalcomputedfon
 tsize=&quot;16&quot;&gt;Integrating Explainability into Machine Learning Models&lt;strong&gt;
 &lt;br /&gt;&lt;/strong&gt;&lt;/span&gt;&lt;strong&gt;&lt;span data-originalfontsize=&quot;12pt&quot; data-orig
 inalcomputedfontsize=&quot;16&quot;&gt;Speaker:&lt;/span&gt;&lt;/strong&gt;&lt;span class=&quot;m_372584988
 9302545826apple-converted-space&quot;&gt;&amp;nbsp\;&lt;/span&gt;&lt;span data-originalfontsize
 =&quot;12pt&quot; data-originalcomputedfontsize=&quot;16&quot;&gt;Dr. Zahid Islam\, CSIRO&lt;/span&gt;&lt;
 u&gt;&lt;/u&gt;&lt;u&gt;&lt;/u&gt;&lt;/p&gt;\n&lt;p class=&quot;m_3725849889302545826mb-4&quot;&gt;&lt;strong&gt;&lt;span data
 -originalfontsize=&quot;12pt&quot; data-originalcomputedfontsize=&quot;16&quot;&gt;Date/Time:&lt;/sp
 an&gt;&lt;/strong&gt;&lt;span class=&quot;m_3725849889302545826apple-converted-space&quot;&gt;&amp;nbsp
 \;&lt;/span&gt;&lt;span data-originalfontsize=&quot;12pt&quot; data-originalcomputedfontsize=
 &quot;16&quot;&gt;10-11am\, Friday 3/3/2023&lt;br /&gt;&lt;/span&gt;&lt;strong&gt;&lt;span data-originalfont
 size=&quot;12pt&quot; data-originalcomputedfontsize=&quot;16&quot;&gt;Venue:&lt;/span&gt;&lt;/strong&gt;&lt;span
  class=&quot;m_3725849889302545826apple-converted-space&quot;&gt;&amp;nbsp\;&lt;/span&gt;&lt;span da
 ta-originalfontsize=&quot;12pt&quot; data-originalcomputedfontsize=&quot;16&quot;&gt;Online via M
 S Teams. A link will be emailed prior to the seminar.&lt;u&gt;&lt;/u&gt;&lt;u&gt;&lt;/u&gt;&lt;/span&gt;
 &lt;/p&gt;\n&lt;p class=&quot;m_3725849889302545826mb-4&quot;&gt;&lt;strong&gt;&lt;span data-originalfont
 size=&quot;12pt&quot; data-originalcomputedfontsize=&quot;16&quot;&gt;RSVP:&lt;/span&gt;&lt;/strong&gt; &lt;a hr
 ef=&quot;https://www.meetup.com/en-AU/canberradatasci/events/291927245/&quot; target
 =&quot;_blank&quot; rel=&quot;noopener&quot; data-saferedirecturl=&quot;https://www.google.com/url?
 q=https://www.meetup.com/en-AU/canberradatasci/events/291927245/&amp;amp\;sour
 ce=gmail&amp;amp\;ust=1677649864719000&amp;amp\;usg=AOvVaw3njBHUulBrYvPdTfd_eVTS&quot; 
 data-removefontsize=&quot;true&quot; data-originalcomputedfontsize=&quot;16&quot;&gt;https://www.
 meetup.com/en-AU/&lt;wbr /&gt;canberradatasci/events/&lt;wbr /&gt;291927245/&lt;/a&gt;&lt;u&gt;&lt;/u
 &gt;&lt;u&gt;&lt;/u&gt;&lt;/p&gt;\n&lt;p class=&quot;m_3725849889302545826mb-4&quot;&gt;&lt;strong&gt;&lt;span data-orig
 inalfontsize=&quot;12pt&quot; data-originalcomputedfontsize=&quot;16&quot;&gt;Abstract:&lt;/span&gt;&lt;/s
 trong&gt;&lt;span class=&quot;m_3725849889302545826apple-converted-space&quot;&gt;&amp;nbsp\;&lt;/sp
 an&gt;&lt;span data-originalfontsize=&quot;12pt&quot; data-originalcomputedfontsize=&quot;16&quot;&gt;M
 achine learning is everywhere. One of the fundamental goals of developing 
 machine learning models is to reduce loss (measured by some function) and 
 increase accuracy (measure by comparing predictions and ground truth). Oft
 en high performing machine learning models are complex Deep Neural Network
  which performs numerical computation based on inputs and many parameters.
  Loss and accuracy metrices drive the computations in the network. However
 \, the metrices are not indicative of the actual reasoning performed inter
 nally by the models. High performing model can erroneously give good predi
 ctions by incorrect reasoning. In this talk I will discuss how explainabil
 ity can help build reliable machine learning models in practice.&lt;u&gt;&lt;/u&gt;&lt;u&gt;
 &lt;/u&gt;&lt;/span&gt;&lt;/p&gt;\n&lt;p class=&quot;m_3725849889302545826mb-4&quot;&gt;&lt;strong&gt;&lt;span data-o
 riginalfontsize=&quot;12pt&quot; data-originalcomputedfontsize=&quot;16&quot;&gt;Bio:&lt;/span&gt;&lt;/str
 ong&gt;&lt;span class=&quot;m_3725849889302545826apple-converted-space&quot;&gt;&amp;nbsp\;&lt;/span
 &gt;&lt;span data-originalfontsize=&quot;12pt&quot; data-originalcomputedfontsize=&quot;16&quot;&gt;I a
 m a post-doctoral fellow in the Conservation Decisions Team of CSIRO&#39;s Env
 ironment business unit. I am in the Machine Learning and Artificial Intell
 igence (MLAI) FSP. My interest is in the pragmatic applications of MLAI. M
 y research is focused on Explainable Artificial Intelligence (XAI). I have
  been trying to explain complex time series models developed using deep ne
 ural networks and graph neural networks to humans. In doing so\, I have be
 en exploring any latent relationships between features and targets.&lt;u&gt;&lt;/u&gt;
 &lt;u&gt;&lt;/u&gt;&lt;/span&gt;&lt;/p&gt;\n&lt;p class=&quot;m_3725849889302545826mb-4&quot;&gt;&lt;span data-origin
 alfontsize=&quot;12pt&quot; data-originalcomputedfontsize=&quot;16&quot;&gt;I obtained a PhD in I
 nformation Sciences from the University of South Australia. Within my PhD\
 , I developed ensemble methods for text classification incorporating XAI. 
 I have also completed an MSc in Computer Science from St Francis Xavier Un
 iversity\, Canada. As part of my MSc\, I developed a framework for healthc
 are workflow verification using Computation Tree Logic (CTL). I have obtai
 ned a BSc in Computer Science and Engineering from Khulna University\, Ban
 gladesh. In between studies\, I have worked as part of the teaching facult
 y at Khulna University\, Bangladesh and as a software engineer at differen
 t organizations.&lt;/span&gt;&lt;/p&gt;
END:VEVENT
END:VCALENDAR