BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Drupal iCal API//EN
X-WR-CALNAME:Events items teaser
X-WR-TIMEZONE:America/Toronto
BEGIN:VTIMEZONE
TZID:America/Toronto
X-LIC-LOCATION:America/Toronto
BEGIN:DAYLIGHT
TZNAME:EDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
DTSTART:20200308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
DTSTART:20191103T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:69b05b87ed2d7
DTSTART;TZID=America/Toronto:20201005T093000
SEQUENCE:0
TRANSP:TRANSPARENT
DTEND;TZID=America/Toronto:20201005T093000
URL:https://uwaterloo.ca/artificial-intelligence-group/events/phd-defence-c
 omputational-mechanisms-language-understanding
LOCATION:Online 200 University Avenue West Waterloo ON N2L 3G1 Canada
SUMMARY:PhD Defence: Computational Mechanisms of Language Understanding and
 \nUse in the Brain and Behaviour
CLASS:PUBLIC
DESCRIPTION:PLEASE NOTE: THIS PHD DEFENCE WILL BE GIVEN ONLINE.\n\nIVANA KA
 JIĆ\, PHD CANDIDATE\n_David R. Cheriton School of Computer Science_\n\nS
 UPERVISOR: Professor Chris Eliasmith
DTSTAMP:20260310T175728Z
END:VEVENT
BEGIN:VEVENT
UID:69b05b87eebaa
DTSTART;TZID=America/Toronto:20200923T130000
SEQUENCE:0
TRANSP:TRANSPARENT
DTEND;TZID=America/Toronto:20200923T130000
URL:https://uwaterloo.ca/artificial-intelligence-group/events/masters-thesi
 s-presentation-sentiment-lexicon-induction-and
LOCATION:Online 200 University Avenue West Waterloo ON N2L 3G1 Canada
SUMMARY:Master’s Thesis Presentation: Sentiment Lexicon Induction and\nIn
 terpretable Multiple-instance Learning in Financial Markets
CLASS:PUBLIC
DESCRIPTION:PLEASE NOTE: THIS MASTER’S THESIS PRESENTATION WILL BE GIVEN 
 ONLINE.\n\nCHENGYAO FU\, MASTER’S CANDIDATE\n_David R. Cheriton School 
 of Computer Science_\n\nSUPERVISORS: Professors Alan Huang and Yuying Li\n
 \nSentiment analysis has been widely used in the domain of finance.\nThere
  are two most common textual sentiment analysis methods in\nfinance: \\tex
 tit{dictionary-based approach} and \\textit{machine\nlearning approach}.
DTSTAMP:20260310T175728Z
END:VEVENT
BEGIN:VEVENT
UID:69b05b87efb78
DTSTART;TZID=America/Toronto:20200923T110000
SEQUENCE:0
TRANSP:TRANSPARENT
DTEND;TZID=America/Toronto:20200923T110000
URL:https://uwaterloo.ca/artificial-intelligence-group/events/masters-thesi
 s-presentation-affective-and-human-virtual
LOCATION:Online 200 University Avenue West Waterloo ON N2L 3G1 Canada
SUMMARY:Master’s Thesis Presentation: Affective and Human-Like Virtual\nA
 gents
CLASS:PUBLIC
DESCRIPTION:PLEASE NOTE: THIS MASTER’S THESIS PRESENTATION WILL BE GIVEN 
 ONLINE.\n\nNEIL BUDNARAIN\, MASTER’S CANDIDATE\n_David R. Cheriton Scho
 ol of Computer Science_\n\nSUPERVISOR: Professor Jesse Hoey
DTSTAMP:20260310T175728Z
END:VEVENT
BEGIN:VEVENT
UID:69b05b87f0a1e
DTSTART;TZID=America/Toronto:20200917T160000
SEQUENCE:0
TRANSP:TRANSPARENT
DTEND;TZID=America/Toronto:20200917T160000
URL:https://uwaterloo.ca/artificial-intelligence-group/events/phd-seminar-p
 roblems-and-opportunities-training-deep
LOCATION:Online 200 University Avenue West Waterloo ON N2L 3G1 Canada
SUMMARY:PhD Seminar: Problems and Opportunities in Training Deep Learning\n
 Software Systems: An Analysis of Variance
CLASS:PUBLIC
DESCRIPTION:PLEASE NOTE: THIS PHD SEMINAR WILL BE GIVEN ONLINE.\n\nHUNG PHA
 M\, PHD CANDIDATE\n_David R. Cheriton School of Computer Science_\n\nSUPE
 RVISORS: Professors Lin Tan and Yaoliang Yu
DTSTAMP:20260310T175728Z
END:VEVENT
BEGIN:VEVENT
UID:69b05b87f1d11
DTSTART;TZID=America/Toronto:20200909T100000
SEQUENCE:0
TRANSP:TRANSPARENT
DTEND;TZID=America/Toronto:20200909T100000
URL:https://uwaterloo.ca/artificial-intelligence-group/events/masters-thesi
 s-presentation-disentangled-syntax-and
LOCATION:Online 200 University Avenue West Waterloo ON N2L 3G1 Canada
SUMMARY:Master’s Thesis Presentation: Disentangled Syntax and Semantics f
 or\nStylized Text Generation
CLASS:PUBLIC
DESCRIPTION:PLEASE NOTE: THIS MASTER’S THESIS PRESENTATION WILL BE GIVEN 
 ONLINE.\n\nYAO LU\, MASTER’S CANDIDATE\n_David R. Cheriton School of Co
 mputer Science_\n\nSUPERVISOR: Professor Olga Vechtomova
DTSTAMP:20260310T175728Z
END:VEVENT
BEGIN:VEVENT
UID:69b05b87f2c7b
DTSTART;TZID=America/Toronto:20200805T123000
SEQUENCE:0
TRANSP:TRANSPARENT
DTEND;TZID=America/Toronto:20200805T123000
URL:https://uwaterloo.ca/artificial-intelligence-group/events/masters-thesi
 s-presentation-variational-inference-text
LOCATION:Online 200 University Avenue West Waterloo ON N2L 3G1 Canada
SUMMARY:Master’s Thesis Presentation: Variational Inference for Text\nGen
 eration: Improving the Posterior
CLASS:PUBLIC
DESCRIPTION:PLEASE NOTE: THIS MASTER’S THESIS PRESENTATION WILL BE GIVEN 
 ONLINE.\n\nVIKASH BALASUBRAMANIAN\, MASTER’S CANDIDATE\n_David R. Cheri
 ton School of Computer Science_\n\nLearning useful representations of data
  is a crucial task in machine\nlearning with wide ranging applications. In
  this thesis we explore\nimproving representations of models based on vari
 ational inference by\nimproving the posterior.
DTSTAMP:20260310T175728Z
END:VEVENT
BEGIN:VEVENT
UID:69b05b87f3e07
DTSTART;TZID=America/Toronto:20200805T100000
SEQUENCE:0
TRANSP:TRANSPARENT
DTEND;TZID=America/Toronto:20200805T100000
URL:https://uwaterloo.ca/artificial-intelligence-group/events/masters-thesi
 s-presentation-dynamic-fusion-techniques
LOCATION:Online 200 University Avenue West Waterloo ON N2L 3G1 Canada
SUMMARY:Master’s Thesis Presentation: Dynamic Fusion Techniques for\nEffe
 ctive Multimodal Deep Learning
CLASS:PUBLIC
DESCRIPTION:PLEASE NOTE: THIS MASTER’S THESIS PRESENTATION WILL BE GIVEN 
 ONLINE.\n\nGAURAV SAHU\, MASTER’S CANDIDATE\n_David R. Cheriton School 
 of Computer Science_\n\nEffective fusion of data from multiple modalities\
 , such as video\,\nspeech\, and text\, is a challenging task due to the he
 terogeneous\nnature of multimodal data. In this work\, we propose fusion t
 echniques\nthat aim to model context from different modalities effectively
 .\nInstead of defining a deterministic fusion operation\, such as\nconcate
 nation\, for the network\, we let the network decide how to\ncombine given
  multimodal features more effectively.
DTSTAMP:20260310T175728Z
END:VEVENT
BEGIN:VEVENT
UID:69b05b8800b13
DTSTART;TZID=America/Toronto:20200804T090000
SEQUENCE:0
TRANSP:TRANSPARENT
DTEND;TZID=America/Toronto:20200804T090000
URL:https://uwaterloo.ca/artificial-intelligence-group/events/masters-thesi
 s-presentation-data-augmentation-text
LOCATION:Online 200 University Avenue West Waterloo ON N2L 3G1 Canada
SUMMARY:Master’s Thesis Presentation: Data Augmentation for Text\nClassif
 ication Tasks
CLASS:PUBLIC
DESCRIPTION:PLEASE NOTE: THIS MASTER’S THESIS PRESENTATION WILL BE GIVEN 
 ONLINE.\n\nDANIEL TAMMING\, MASTER’S CANDIDATE\n_David R. Cheriton Scho
 ol of Computer Science_\n\nThanks to increases in computing power and the 
 growing availability of\nlarge datasets\, neural networks have achieved st
 ate of the art results\nin many natural language processing (NLP) and comp
 uter vision (CV)\ntasks. These models require a large number of training e
 xamples that\nare balanced between classes\, but in many application areas
  they rely\non training sets that are either small or imbalanced\, or both
 . To\naddress this\, data augmentation has become standard practice in CV.
 \nThis research is motivated by the observation that\, relative to CV\,\nd
 ata augmentation is underused and understudied in NLP.
DTSTAMP:20260310T175728Z
END:VEVENT
BEGIN:VEVENT
UID:69b05b8801896
DTSTART;TZID=America/Toronto:20200730T130000
SEQUENCE:0
TRANSP:TRANSPARENT
DTEND;TZID=America/Toronto:20200730T130000
URL:https://uwaterloo.ca/artificial-intelligence-group/events/masters-thesi
 s-presentation-decay-makes-supervised
LOCATION:Online 200 University Avenue West Waterloo ON N2L 3G1 Canada
SUMMARY:Master’s Thesis Presentation: Decay Makes Supervised Predictive\n
 Coding Generative
CLASS:PUBLIC
DESCRIPTION:PLEASE NOTE: THIS MASTER’S THESIS PRESENTATION WILL BE GIVEN 
 ONLINE.\n\nWEI SUN\, MASTER’S CANDIDATE\n_David R. Cheriton School of C
 omputer Science_\n\nPredictive Coding is a hierarchical model of neural co
 mputation that\napproximates backpropagation using only local computations
  and local\nlearning rules. An important aspect of Predictive Coding is th
 e\npresence of feedback connections between layers. These feedback\nconnec
 tions allow Predictive Coding networks to potentially be\ngenerative as we
 ll as discriminative. However\, Predictive Coding\nnetworks trained on sup
 ervised classification tasks cannot generate\naccurate input samples close
  to the training inputs from the class\nvectors alone.
DTSTAMP:20260310T175728Z
END:VEVENT
BEGIN:VEVENT
UID:69b05b88022e0
DTSTART;TZID=America/Toronto:20200526T100000
SEQUENCE:0
TRANSP:TRANSPARENT
DTEND;TZID=America/Toronto:20200526T100000
URL:https://uwaterloo.ca/artificial-intelligence-group/events/masters-thesi
 s-presentation-analysis-textual-and-non-textual
LOCATION:Online 200 University Avenue West Waterloo ON N2L 3G1 Canada
SUMMARY:Master’s Thesis Presentation: Analysis of Textual and Non-Textual
 \nSources of Sentiment in GitHub
CLASS:PUBLIC
DESCRIPTION:PLEASE NOTE: THIS MASTER’S THESIS PRESENTATION WILL BE GIVEN 
 ONLINE.\n\nNALIN DE ZOYSA\, MASTER’S CANDIDATE\n_David R. Cheriton Scho
 ol of Computer Science_\n\nGitHub is a collaborative platform that is used
  primarily for the\ndevelopment of software. In order to gain more insight
  into how teams\nwork on GitHub\, we wish to analyze the sentiment content
  available via\ncommunication on the platform.
DTSTAMP:20260310T175728Z
END:VEVENT
END:VCALENDAR