BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260808T165220Z
UID:98366060-ecc8-4b04-a7af-37805b860d3d
DTSTART:20220105T074500Z
DTEND:20220105T160000Z
DESCRIPTION:\n\nAnnotation\n\nApplications for natural language processing 
 (NLP) have exploded in the pastdecade. With the proliferation AI assistant
 s and organizations infusing their businesses with more interactive human-
 machine experiences\, understanding how NLP techniques can be used to mani
 pulate analyze\, and generate text-based data is essential. Modern techniq
 ues can capture the nuance\, context and sophistication of language just a
 s humans do. And when designed correctly\, developers can use these techn
 iques to build powerful NLP applications that provide natural and seamless
  human-computer interactions within chatbots\, AI voice agents\, and more
 . Deep learning models have gained widespread popularity for NLP because o
 f their ability to accurately generalize over a range of contexts and lang
 uages. Transformer-based models\, such as Bidirectional Encoder Representa
 tions from Transformers (BERT)\, have revolutionized NLP offering accuracy
  comparable to human baselines on benchmarks like SQuAD for question-answe
 r\, entity recognition\, intent recognition\, sentiment analysis\, and mor
 e.\n\nIn this workshop\, you’ll learn how to use Transformer-based natur
 al language processing models for text classification tasks\, such as cat
 egorizing documents. You’ll also learn how to leverage Transformer-based
  models for named-entity recognition (NER) tasks and how to analyze variou
 s model features\, constraints\, and characteristics to determine which mo
 del is best suited for a particular use case based on metrics\, domain spe
 cificity\, and available resources.\n\nThis course is only offered to acad
 emia (see details below in section Capacity and Fees).\n\nLevel\n\ninter
 mediate-advanced\n\nLanguage\n\nEnglish\n\nPurpose of the course (benefit
 s for the attendees)\n\n\n	Understand how text embeddings have rapidly evo
 lved in NLP tasks such as Word2Vec\, recurrent neural network (RNN)-base
 d embeddings\, and Transformers\n	See how Transformer architecture featur
 es\, especially self-attention\, are used to create language models with
 out RNNs\n	Use self-supervision to improve the Transformer architecture in
  BERT\, Megatron\, and other variants for superior NLP results \n	Lever
 age pre-trained\, modern NLP models to solve multiple tasks such as text 
 classification\, NER\, and question answering\n	Manage inference challeng
 es and deploy refined models for live applications\n\n\nPrerequisites\n\n\
 n	Experience with Python coding and use of library functions and paramete
 rs\n	Fundamental understanding of a deep learning framework such as Tenso
 rFlow\, PyTorch\, or Keras\n	Basic understanding of neural networks\n\n\nA
 bout the tutor\n\nGeorg Zitzlsberger is a research specialist for Machine
  and Deep Learning. He received his certification from Nvidia as a Univers
 ity Ambassador of the Nvidia Deep Learning Institute (DLI) program. This c
 ertification allows him to offer Nvidia DLI courses to academic users of I
 T4Innovations' HPC services.\n\nNVIDIA Deep Learning Institute\n\nThe NVI
 DIA Deep Learning Institute delivers hands-on training for developers\, d
 ata scientists\, and engineers. The program is designed to help you get st
 arted with training\, optimizing\, and deploying neural networks to solve 
 real-world problems across diverse industries such as self-driving cars\, 
 healthcare\, online services\, and robotics.\n\nAcknowledgements\n\nThis c
 ourse  is sponsored by NVIDIA as part of the NVIDIA Deep Learning Institu
 te (DLI) University Ambassador program.\n\n                \n\nTh
 is event was partially supported by The Ministry of Education\, Youth and 
 Sports from the Large Infrastructures for Research\, Experimental Developm
 ent and Innovations project "e-Infrastruktura CZ – LM2018140“ and part
 ially by the PRACE-6IP project - the European Union’s Horizon 2020 resea
 rch and innovation programme under grant agreement No. 823767.\n\n\n\n \n
 https://events.prace-ri.eu/event/1302/
SUMMARY:[ONLINE] Building Transformer-Based Natural Language Processing App
 lications @ IT4Innovations
URL;VALUE=URI:https://events.prace-ri.eu/event/1302/
END:VEVENT
END:VCALENDAR