BEGIN:VCALENDAR VERSION:2.0 PRODID:-//HasGeek//NONSGML Funnel//EN DESCRIPTION:A conference on deep learning. X-WR-CALDESC:A conference on deep learning. NAME:Deep Learning Conf 2016 X-WR-CALNAME:Deep Learning Conf 2016 REFRESH-INTERVAL;VALUE=DURATION:PT12H SUMMARY:Deep Learning Conf 2016 TIMEZONE-ID:Asia/Kolkata X-PUBLISHED-TTL:PT12H X-WR-TIMEZONE:Asia/Kolkata BEGIN:VEVENT SUMMARY:Check-in and breakfast DTSTART:20160701T031500Z DTEND:20160701T035000Z DTSTAMP:20260421T165024Z UID:session/7Qxtwi5a1vhzgZZFoNrCpA@hasgeek.com SEQUENCE:0 CREATED:20160519T112751Z DESCRIPTION:\n LAST-MODIFIED:20160617T142135Z LOCATION:Auditorium - CMRIT College\nIN ORGANIZER;CN="The Fifth Elephant":MAILTO:no-reply@hasgeek.com BEGIN:VALARM ACTION:display DESCRIPTION:Check-in and breakfast in Auditorium in 5 minutes TRIGGER:-PT5M END:VALARM END:VEVENT BEGIN:VEVENT SUMMARY:Introduction to the conference and team DTSTART:20160701T035000Z DTEND:20160701T040000Z DTSTAMP:20260421T165024Z UID:session/G571e54i3UYMqixddNjrtb@hasgeek.com SEQUENCE:0 CREATED:20160519T112814Z DESCRIPTION:\n LAST-MODIFIED:20160519T112912Z LOCATION:Auditorium - CMRIT College\nIN ORGANIZER;CN="The Fifth Elephant":MAILTO:no-reply@hasgeek.com BEGIN:VALARM ACTION:display DESCRIPTION:Introduction to the conference and team in Auditorium in 5 min utes TRIGGER:-PT5M END:VALARM END:VEVENT BEGIN:VEVENT SUMMARY:Deep learning: A convoluted overview with recurrent themes and bel iefs. DTSTART:20160701T040000Z DTEND:20160701T050000Z DTSTAMP:20260421T165024Z UID:session/Pr1QHhXpxeQzGYxg68MX5X@hasgeek.com SEQUENCE:2 CATEGORIES:Full talk,Intermediate CREATED:20160610T113431Z DESCRIPTION:The talk is meant to serve as an overview for the conference. It will briefly describe the history and origin of deep learning\, how it contrasts with 'traditional' machine learning\, and touching upon the domi nant concepts that shape its practice today.\n\n### Speaker bio\n\nDr. Ana nd Chandrasekaran is a founder and the CTO of Mad Street Den\, an AI compa ny specializing in computer vision. In addition to an academic background in the fields of neuroscience and neuromorphic engineering\, he has been a member of teams working on DARPA projects in cognition and vision.\n LAST-MODIFIED:20230810T072606Z LOCATION:Auditorium - CMRIT College\nIN ORGANIZER;CN="The Fifth Elephant":MAILTO:no-reply@hasgeek.com URL:https://hasgeek.com/fifthelephant/deep-learning-2016/schedule/deep-lea rning-a-convoluted-overview-with-recurrent-themes-and-beliefs-Pr1QHhXpxeQz GYxg68MX5X BEGIN:VALARM ACTION:display DESCRIPTION:Deep learning: A convoluted overview with recurrent themes and beliefs. in Auditorium in 5 minutes TRIGGER:-PT5M END:VALARM END:VEVENT BEGIN:VEVENT SUMMARY:Sponsored session: Recent advancements in Deep Learning techniques using GPUs. DTSTART:20160701T050000Z DTEND:20160701T054500Z DTSTAMP:20260421T165024Z UID:session/SgQua9PFgdL2aeNTBwPa5P@hasgeek.com SEQUENCE:2 CATEGORIES:Sponsored talk,Intermediate CREATED:20160610T113914Z DESCRIPTION:Evolution of Deep Learning (DL) techniques - Over view of mode rn DL stack (software and hardware)- Advances in GPU computation and how i t helps to dramatically bring down DL training time - Modern tools CuDNN\, CuSPARSE\, cuBLAS\, DIGITS-NCCL to improve intranode and internode scalin g - Success Stories - DL Ecosystem in India from Enteprise and Startups pe rspective.\n\n### Speaker bio\n\nMr. Sundara R Nagalingam is the Head of M anufacturing and Energy businesses for NVIDIA India. He is also responsib le for managing the Deep Learning business ecosystem for the company.\n\nH e has twenty years of experience in solutions involving Visual Computing\, Virtualization and High Performance Computing. He also has exposure to th e work cultures of multiple countries in the Asia Pacific region.\n\nHe ha s a strong technical background and his areas of interest include Deep Lea rning\, Big Data Analytics\, IoT and Automotive Solutions.\n LAST-MODIFIED:20230810T072606Z LOCATION:Auditorium - CMRIT College\nIN ORGANIZER;CN="The Fifth Elephant":MAILTO:no-reply@hasgeek.com URL:https://hasgeek.com/fifthelephant/deep-learning-2016/schedule/recent-a dvancements-in-deep-learning-techniques-using-gpus-SgQua9PFgdL2aeNTBwPa5P BEGIN:VALARM ACTION:display DESCRIPTION:Sponsored session: Recent advancements in Deep Learning techni ques using GPUs. in Auditorium in 5 minutes TRIGGER:-PT5M END:VALARM END:VEVENT BEGIN:VEVENT SUMMARY:Morning tea break DTSTART:20160701T054500Z DTEND:20160701T061500Z DTSTAMP:20260421T165024Z UID:session/4MFW49cd1y5U2SSK27CTjN@hasgeek.com SEQUENCE:0 CREATED:20160519T112952Z DESCRIPTION:\n LAST-MODIFIED:20160610T114112Z LOCATION:Auditorium - CMRIT College\nIN ORGANIZER;CN="The Fifth Elephant":MAILTO:no-reply@hasgeek.com BEGIN:VALARM ACTION:display DESCRIPTION:Morning tea break in Auditorium in 5 minutes TRIGGER:-PT5M END:VALARM END:VEVENT BEGIN:VEVENT SUMMARY:Applied Deep Learning DTSTART:20160701T061500Z DTEND:20160701T070000Z DTSTAMP:20260421T165024Z UID:session/AKD8uSKXKch3cGnc3Et96b@hasgeek.com SEQUENCE:2 CATEGORIES:Full talk,Intermediate CREATED:20160606T045646Z DESCRIPTION:The talk consists of an introduction to deep learning followed by live examples on the implementation of deepnets using python. The talk then discusses how to optimize the parameters of a neural network and how to carefully choose the hyperparameters. Afterwards\, we move to pretrain ed networks and methods of finetuning a pretrained network. The talk will show use of python with keras and Caffe.\n\n### Speaker bio\n\nI currently work as a Senior Data Scientist at Searchmetrics Inc. in Berlin\, Germany . \n\nI have participated in over 100 machine learning competitions and th e knowledge acquired by them are put to use in my daily job. I also develo ped an AutoML system based on the knowledge gained from the wide range of datasets Ive worked with. The AutoML system recently won the final phase o f AutoML cpu track and the neural network framework won the only GPU track of the competition.\n\nMore information about me can be found at: www.bit .ly/thakurabhishek and on www.kaggle.com/abhishek\n LAST-MODIFIED:20230810T072606Z LOCATION:Auditorium - CMRIT College\nIN ORGANIZER;CN="The Fifth Elephant":MAILTO:no-reply@hasgeek.com URL:https://hasgeek.com/fifthelephant/deep-learning-2016/schedule/applied- deep-learning-AKD8uSKXKch3cGnc3Et96b BEGIN:VALARM ACTION:display DESCRIPTION:Applied Deep Learning in Auditorium in 5 minutes TRIGGER:-PT5M END:VALARM END:VEVENT BEGIN:VEVENT SUMMARY:Residual Learning and Stochastic Depth in Deep Neural Networks DTSTART:20160701T070000Z DTEND:20160701T072000Z DTSTAMP:20260421T165024Z UID:session/4MFsKQvu6djBgpnbZ6Arsk@hasgeek.com SEQUENCE:2 CATEGORIES:Crisp talk,Intermediate CREATED:20160609T142122Z DESCRIPTION:Residual networks are famed for receiving first place in lates t ILSVRC image classification.\nThey are able to achieve a start of the ar t performance in image classification tasks beating previous VGG net\nStoc hastic Depth is a ridiculously simple idea which can help in training the network even if the maximum depth is in order of 1000s.\n\nThe talk would cover the following:\n1. Introduction to convolution layer\, batch normali zation and relu depending on the audience comfort level with these concept s.\n2. Basic Introduction of architectures of Deep Neural Networks which p reviously won ILSVRC\n3. Deep Residual Learning and how to implement Resid ual networks in TensorFlow\n4. Deep Neural Networks with Stochastic depth\ n5. If time permits will discuss other similar architectures like Recombin ator Networks and summation based networks.\n\n### Speaker bio\n\nPradyumn a is a Statistical Analyst at @WalmartLabs. He completed his under graduat ion in Computer Science from BITS Pilani Goa Campus. He did his undergradu ate thesis under Prof Yogesh Rathi\, Director of Pediatric Image Computing at Psychiatry Neuroimaging Lab Harvard Medical School. He was also a Memb er of Board of Reviewers at 23rd WSCG International Conference on Computer Graphics\, Visualization and Computer Vision 2015.\n LAST-MODIFIED:20230810T072606Z LOCATION:Auditorium - CMRIT College\nIN ORGANIZER;CN="The Fifth Elephant":MAILTO:no-reply@hasgeek.com URL:https://hasgeek.com/fifthelephant/deep-learning-2016/schedule/residual -learning-and-stochastic-depth-in-deep-neural-networks-4MFsKQvu6djBgpnbZ6A rsk BEGIN:VALARM ACTION:display DESCRIPTION:Residual Learning and Stochastic Depth in Deep Neural Networks in Auditorium in 5 minutes TRIGGER:-PT5M END:VALARM END:VEVENT BEGIN:VEVENT SUMMARY:Expresso - A user-friendly tool for Deep Learning DTSTART:20160701T072000Z DTEND:20160701T074000Z DTSTAMP:20260421T165024Z UID:session/GqhhiJZu1xBLcv5hfamVRw@hasgeek.com SEQUENCE:2 CATEGORIES:Crisp talk,Beginner CREATED:20160611T080623Z DESCRIPTION:Talk will focus on giving an insight about challenges faced wh ile designing GUI for Deep-learning. It will also include Live Demo of tra ining and visualization of CNN via Expresso.\n\n### Speaker bio\n\nJaley D holakiya is an alumni of Video Analytics Lab at Indian Institute of Scienc e. He is core-developer of Expresso\, a user-friendly GUI build atop Caffe .Currently\, he is working on Recommender Systems in Vizury.\n LAST-MODIFIED:20230810T072606Z LOCATION:Auditorium - CMRIT College\nIN ORGANIZER;CN="The Fifth Elephant":MAILTO:no-reply@hasgeek.com URL:https://hasgeek.com/fifthelephant/deep-learning-2016/schedule/expresso -a-user-friendly-tool-for-deep-learning-GqhhiJZu1xBLcv5hfamVRw BEGIN:VALARM ACTION:display DESCRIPTION:Expresso - A user-friendly tool for Deep Learning in Auditori um in 5 minutes TRIGGER:-PT5M END:VALARM END:VEVENT BEGIN:VEVENT SUMMARY:Lunch DTSTART:20160701T074000Z DTEND:20160701T084000Z DTSTAMP:20260421T165024Z UID:session/4GVfixAD4SdL4oAfQeMHJo@hasgeek.com SEQUENCE:0 CREATED:20160519T113444Z DESCRIPTION:\n LAST-MODIFIED:20160530T085620Z LOCATION:Auditorium - CMRIT College\nIN ORGANIZER;CN="The Fifth Elephant":MAILTO:no-reply@hasgeek.com BEGIN:VALARM ACTION:display DESCRIPTION:Lunch in Auditorium in 5 minutes TRIGGER:-PT5M END:VALARM END:VEVENT BEGIN:VEVENT SUMMARY:Joint Training of a Convolutional Network and a Graphical Model fo r Human Pose Estimation DTSTART:20160701T084000Z DTEND:20160701T090000Z DTSTAMP:20260421T165024Z UID:session/6tFwFgQxTphfYykq5uYhAB@hasgeek.com SEQUENCE:2 CATEGORIES:Crisp talk,Advanced CREATED:20160523T065413Z DESCRIPTION:http://arxiv.org/pdf/1406.2984v2.pdf\n\n### Speaker bio\n\nArj un Jain is the cofounder of Perceptive Code. Prior to this\, he was resear cher with a special project team at Apple and a post-doctoral researcher a t the Computer Science department at New York University's Courant Institu te. He received his Ph.D. in Computer Science from the Max-Planck Institut e for Informatics in Germany. Broadly\, his research lies at the interface of computer graphics\, computer vision\, and machine learning\, with a fo cus on human pose estimation and data-driven artistic content creation too ls. Arjun has worked as a developer for several companies\, including Yaho o! in Bangalore and Weta Digital in New Zealand. Arjun served as a develop er for Weta Digital’s vision-based motion capture system. This system ha s been used in many feature films\, and Arjun was credited for his work in Steven Spielberg’s\, The Adventures of Tintin. Arjun’s work has resul ted in several academic publications\, a patent\, and has been featured by mainstream media\, including in the magazines: New Scientist\, Discovery\ , BCC\, Vogue\, Wired\, India Today\, and The Hollywood Reporter\, among o ther outlets.\n LAST-MODIFIED:20230810T072606Z LOCATION:Auditorium - CMRIT College\nIN ORGANIZER;CN="The Fifth Elephant":MAILTO:no-reply@hasgeek.com URL:https://hasgeek.com/fifthelephant/deep-learning-2016/schedule/joint-tr aining-of-a-convolutional-network-and-a-graphical-model-for-human-pose-est imation-6tFwFgQxTphfYykq5uYhAB BEGIN:VALARM ACTION:display DESCRIPTION:Joint Training of a Convolutional Network and a Graphical Mode l for Human Pose Estimation in Auditorium in 5 minutes TRIGGER:-PT5M END:VALARM END:VEVENT BEGIN:VEVENT SUMMARY:Deep Dive Into Building Chat-bots Using Deep Learning DTSTART:20160701T090000Z DTEND:20160701T094500Z DTSTAMP:20260421T165024Z UID:session/SngGdah5W1ZH5hAGZfxtGX@hasgeek.com SEQUENCE:2 CATEGORIES:Full talk,Intermediate CREATED:20160610T114134Z DESCRIPTION:Motivation: exponential growth in information\, limitations of current search interfaces\, consumer expectations\nComponents of building a chat bot: intent extraction\, dialogue generation\, meaningful search\, assistance based conversation\nDeep Learning techniques: Text segmentatio n\, Sequence labeling\, sentence generation\, conversation generation\nDem o and example: A chat bot in fashion commerce domain\n\n### Speaker bio\n\ nVijay Gabale is co-founder and CTO of Infilect\, an AI-powered Commerce P latform. Infilect has been building a fashion commerce platform to provide exceptional shopping experiences to the Internet consumers. The company h as made several innovations in deep learning to process rich multi-media d ata (text\, image\, videos) to improve discovery\, search and personalizat ion experiences of online consumers.\n\nPrior to co-founding Infilect\, he was a research scientist with IBM Research Labs. He graduated with a PhD from IIT Bombay\, India in 2012. He has several top tier research publicat ions and software patents to his name. He is also co-organizer of ‘Deep Learning Bangalore’ meetup. He has been actively working in deep learnin g for past several years and has give several talks in and outside India o n the research and applications of deep learning in e-commerce.\n LAST-MODIFIED:20230810T072606Z LOCATION:Auditorium - CMRIT College\nIN ORGANIZER;CN="The Fifth Elephant":MAILTO:no-reply@hasgeek.com URL:https://hasgeek.com/fifthelephant/deep-learning-2016/schedule/deep-div e-into-building-chat-bots-using-deep-learning-SngGdah5W1ZH5hAGZfxtGX BEGIN:VALARM ACTION:display DESCRIPTION:Deep Dive Into Building Chat-bots Using Deep Learning in Audit orium in 5 minutes TRIGGER:-PT5M END:VALARM END:VEVENT BEGIN:VEVENT SUMMARY:BoF - Getting Started with Deep Learning DTSTART:20160701T094500Z DTEND:20160701T103000Z DTSTAMP:20260421T165024Z UID:session/JkYAVBJEapdy9gDY54ez5X@hasgeek.com SEQUENCE:1 CREATED:20160612T140144Z DESCRIPTION:How to get started with Deep Learning?\n LAST-MODIFIED:20230108T103046Z LOCATION:Classroom - CMRIT College\nIN ORGANIZER;CN="The Fifth Elephant":MAILTO:no-reply@hasgeek.com BEGIN:VALARM ACTION:display DESCRIPTION:BoF - Getting Started with Deep Learning in Classroom in 5 min utes TRIGGER:-PT5M END:VALARM END:VEVENT BEGIN:VEVENT SUMMARY:Deep learning for computational pathology DTSTART:20160701T094500Z DTEND:20160701T103000Z DTSTAMP:20260421T165024Z UID:session/NeWoh6u4GvoCCCwGCknjRd@hasgeek.com SEQUENCE:2 CATEGORIES:Full talk,Intermediate CREATED:20160610T114204Z DESCRIPTION:~Introduction to deep learning and computational pathology (C- path)\n~Improtant problems in C-path such as prostate cancer recurrrence p rediction that can be addressed using machine learning\n~Our deep learning based C-path pipeline\n~Important results and future directions\n\n### Sp eaker bio\n\nNeeraj Kumar is a research scholar with the department of ele ctronics and electrical engineering at IIT Guwahati. He has developed lear ning based algorithms for inverse problems such as single image super reso lution and reducing the solution space of Non-negative matrix factorizatio n during his PhD. Towards the end of his PhD he shifted the focus of his r esearch to computational pathology and developed deep learning based pipel ines for automated analysis of histopathological images. For this purpose he has interned for six months at the Beckman Institute and Department of Bioengineering of the University of Illinois at Urban-Champaign. He is the recipient of the prestigious Microsoft research India fellowship and Eras mus Mundus Heritage Fellowship during his PhD.\n LAST-MODIFIED:20230810T072606Z LOCATION:Auditorium - CMRIT College\nIN ORGANIZER;CN="The Fifth Elephant":MAILTO:no-reply@hasgeek.com URL:https://hasgeek.com/fifthelephant/deep-learning-2016/schedule/deep-lea rning-for-computational-pathology-NeWoh6u4GvoCCCwGCknjRd BEGIN:VALARM ACTION:display DESCRIPTION:Deep learning for computational pathology in Auditorium in 5 m inutes TRIGGER:-PT5M END:VALARM END:VEVENT BEGIN:VEVENT SUMMARY:Evening tea break DTSTART:20160701T103000Z DTEND:20160701T110000Z DTSTAMP:20260421T165024Z UID:session/G5CmjgRXGe5AQbWA93vkFX@hasgeek.com SEQUENCE:0 CREATED:20160519T113725Z DESCRIPTION:\n LAST-MODIFIED:20160612T135231Z LOCATION:Bangalore ORGANIZER;CN="The Fifth Elephant":MAILTO:no-reply@hasgeek.com BEGIN:VALARM ACTION:display DESCRIPTION:Evening tea break in 5 minutes TRIGGER:-PT5M END:VALARM END:VEVENT BEGIN:VEVENT SUMMARY:Slot-Filling in Conversations with Deep Learning DTSTART:20160701T110000Z DTEND:20160701T112000Z DTSTAMP:20260421T165024Z UID:session/2CwqqtEEXcjVzP8Tj8SPdh@hasgeek.com SEQUENCE:2 CATEGORIES:Crisp talk,Intermediate CREATED:20160610T114148Z DESCRIPTION:Building Conversational Assistants\nSlot-filling problem\nCRFs \, RNNs\nRNN variations - Elman\, Jordan\, BiRNNs\nOptimizing RNNs for Slo t-Filling\n\n### Speaker bio\n\nNishant Sinha is an experienced computer s cientist and researcher with expertise in deductive and inductive inferenc e\, conversational interfaces and distributed systems. He has worked at re puted industrial research labs including NEC Labs USA and IBM Research Ind ia and mentored several graduate students. He has published in top-tier in ternational academic conferences and has several patents to his credit. At MagicX\, Nishant helps build smart personal assistants for getting tasks done.\n LAST-MODIFIED:20230810T072606Z LOCATION:Auditorium - CMRIT College\nIN ORGANIZER;CN="The Fifth Elephant":MAILTO:no-reply@hasgeek.com URL:https://hasgeek.com/fifthelephant/deep-learning-2016/schedule/slot-fil ling-in-conversations-with-deep-learning-2CwqqtEEXcjVzP8Tj8SPdh BEGIN:VALARM ACTION:display DESCRIPTION:Slot-Filling in Conversations with Deep Learning in Auditorium in 5 minutes TRIGGER:-PT5M END:VALARM END:VEVENT BEGIN:VEVENT SUMMARY:Challenges & Implications of Deep Learning in Healthcare DTSTART:20160701T112000Z DTEND:20160701T120500Z DTSTAMP:20260421T165024Z UID:session/YFsovubSPBTUpqnD3zuuzy@hasgeek.com SEQUENCE:2 CATEGORIES:Full talk,Intermediate CREATED:20160610T114225Z DESCRIPTION:1. Quick recap on milestones achieved by deep learning and in the healthcare space\n2. Open challenges in DL for Medicine – Access to data\, number of samples\, large sizes\, variations based on demographics\ , need for high accuracy solutions\n3. Solution to our winning IEEE-ISBI c hallenge entry on Multiple Sclerosis using 3D CNNs \n4. Current state of a rt in research & industry – how far are we from complete diagnosis?\n\n# ## Speaker bio\n\nSuthirth Vaidya is a co-founder at Predible Health\, whi ch develops AI based recognition tools for medical imaging. His team previ ously won the Grand Challenge at IEEE-International Symposium on Biomedica l Imaging 2015 at New York\, USA for application of deep learning for segm entation of multiple sclerosis lesions in the brain. He underwent his unde rgraduate and master's degree studies from IIT Madras.\n LAST-MODIFIED:20230810T072606Z LOCATION:Auditorium - CMRIT College\nIN ORGANIZER;CN="The Fifth Elephant":MAILTO:no-reply@hasgeek.com URL:https://hasgeek.com/fifthelephant/deep-learning-2016/schedule/challeng es-implications-of-deep-learning-in-healthcare-YFsovubSPBTUpqnD3zuuzy BEGIN:VALARM ACTION:display DESCRIPTION:Challenges & Implications of Deep Learning in Healthcare in Au ditorium in 5 minutes TRIGGER:-PT5M END:VALARM END:VEVENT BEGIN:VEVENT SUMMARY:BoF: Building Chat Bots DTSTART:20160701T112000Z DTEND:20160701T120500Z DTSTAMP:20260421T165024Z UID:session/4LXYZUS8tpHQbw5fbdhFxP@hasgeek.com SEQUENCE:0 CREATED:20160612T140739Z DESCRIPTION:\n LAST-MODIFIED:20160619T082610Z LOCATION:Classroom - CMRIT College\nIN ORGANIZER;CN="The Fifth Elephant":MAILTO:no-reply@hasgeek.com BEGIN:VALARM ACTION:display DESCRIPTION:BoF: Building Chat Bots in Classroom in 5 minutes TRIGGER:-PT5M END:VALARM END:VEVENT BEGIN:VEVENT SUMMARY:Making Deep Neural Networks smaller and faster DTSTART:20160701T120500Z DTEND:20160701T122500Z DTSTAMP:20260421T165024Z UID:session/UohV4HzhtoFdi2tGfhMLAR@hasgeek.com SEQUENCE:2 CATEGORIES:Crisp talk,Intermediate CREATED:20160610T135727Z DESCRIPTION:First\, I shall motivate the general problem of model compress ion and it's relevance for real-world applications.\nThen\, I shall provid e overviews of the following papers:\n1) Learning both Weights and Connect ions for Efficient Neural Networks\, NIPS 2015\n2) Deep Compression\, ICLR 2016\n3) Learning the Architecture of Deep Neural Networks\, arxiv 2016\n \n### Speaker bio\n\nSuraj is a second year Master's student at Video Anal ytics Lab\, Indian Institute of Science. From the past one and a half year s\, he has been working on the problem of model compression. His work has been presented previously at British Machine Vision Conference (BMVC) - 20 15.\n LAST-MODIFIED:20230810T072606Z LOCATION:Auditorium - CMRIT College\nIN ORGANIZER;CN="The Fifth Elephant":MAILTO:no-reply@hasgeek.com URL:https://hasgeek.com/fifthelephant/deep-learning-2016/schedule/making-d eep-neural-networks-smaller-and-faster-UohV4HzhtoFdi2tGfhMLAR BEGIN:VALARM ACTION:display DESCRIPTION:Making Deep Neural Networks smaller and faster in Auditorium i n 5 minutes TRIGGER:-PT5M END:VALARM END:VEVENT BEGIN:VEVENT SUMMARY:Closing remarks and feedback DTSTART:20160701T122500Z DTEND:20160701T124500Z DTSTAMP:20260421T165024Z UID:session/MsBE1rBMC5d84BMnFrAkHv@hasgeek.com SEQUENCE:0 CREATED:20160610T114302Z DESCRIPTION:\n LAST-MODIFIED:20160619T082621Z LOCATION:Auditorium - CMRIT College\nIN ORGANIZER;CN="The Fifth Elephant":MAILTO:no-reply@hasgeek.com BEGIN:VALARM ACTION:display DESCRIPTION:Closing remarks and feedback in Auditorium in 5 minutes TRIGGER:-PT5M END:VALARM END:VEVENT BEGIN:VEVENT SUMMARY:Check-in and Breakfast DTSTART:20160702T024500Z DTEND:20160702T033000Z DTSTAMP:20260421T165024Z UID:session/3m89wBvMHXQD82E6Hw1czK@hasgeek.com SEQUENCE:0 CREATED:20160620T182538Z DESCRIPTION:\n LAST-MODIFIED:20160620T182557Z LOCATION:Bangalore ORGANIZER;CN="The Fifth Elephant":MAILTO:no-reply@hasgeek.com BEGIN:VALARM ACTION:display DESCRIPTION:Check-in and Breakfast in 5 minutes TRIGGER:-PT5M END:VALARM END:VEVENT BEGIN:VEVENT SUMMARY:Introduction to Deep Learning for Natural Language Processing DTSTART:20160702T033000Z DTEND:20160702T053000Z DTSTAMP:20260421T165024Z UID:session/46B6wmXx1NbLfmZbmjznTj@hasgeek.com SEQUENCE:2 CATEGORIES:Workshop,Intermediate CREATED:20160620T175606Z DESCRIPTION:We would cover the following: \n\n1. What is deep learning? \n 2. Motivation: Some use cases where it has produced state-of-art results \ n3. Basic building blocks of Neural networks (Neuron\, activation function \, back propagation algorithm\, gradient descent algorithm) \n4. Supervise d learning (multi-layer perceptron\, recurrent neural network) \n5. Introd uction to word2vec \n6. Introduction to Recurrent Neural Networks \n7. Tex t classification using RNN \n8. Impact of GPUs (Some practical thoughts on hardware and software) \n\nBroadly\, there will be three hands-on modules \n\n1. A simple multi-layer perceptron - to understand basics of neural ne tworks (everything will be coded from scratch) \n2. Vectorization hands-on using Word2vec\n3. A text classification problem and a text generation pr oblem: This will be solved using Recurrent Neural Networks.\n\n### Speaker bio\n\n**Nischal** is co founder and Data Engineer at Unnati Data Labs wh o enables the Data Scientists to work at peace. He makes sure that they ge t the data they need and in the way they need it. Previously he has built\ , from scratch\, various systems for E-commerce like catalog management\, recommendation engines and other systems that amass a lot of data\, during his tenure at Redmart.\n\nAt SAP Labs\, Nischal has built various data cr awlers\, intention mining systems and laid down initial work on an end to end Text Mining/Analysis Pipeline. The majority of his work\, however\, wa s centered around building a system that gamified technical indicators in a product for the Fintech domain.\n\nHe has conducted workshops in the fie ld of Deep learning across the world. He is a strong believer of open sour ce and loves to architect big\, fast and reliable systems. In his free tim e\, he enjoys psychedelic trance and travelling to remote places.\n\n**Rag hotham** is a Data Scientist who can work across the complete stack. Previ ously\, at Touchpoints Inc.\, He single handedly built a data analytics pl atform for a fitness wearable company. With Redmart\, he worked on the CRM system and has built a sentinment analyzer for Redmart's Social Media. Pr ior to Redmart and Touchpoints\, Raghotham worked at SAP Labs where he was a core part of what is currently SAP's framework for building web and mob ile products. He was a part of multiple SAP wide events helping to spread the knowledge both internally and to customers.\n\nHaving found deep love for data science\, neural networks and the passion for teaching\, Raghotha m has conducted workshops across the world. Apart from getting his hands d irty with data\, he loves travelling\, Pink Floyd and masala dosas.\n LAST-MODIFIED:20230810T072606Z LOCATION:Room 2 - Google India Pvt. Ltd\nBengaluru\nIN ORGANIZER;CN="The Fifth Elephant":MAILTO:no-reply@hasgeek.com URL:https://hasgeek.com/fifthelephant/deep-learning-2016/schedule/introduc tion-to-deep-learning-for-natural-language-processing-46B6wmXx1NbLfmZbmjzn Tj BEGIN:VALARM ACTION:display DESCRIPTION:Introduction to Deep Learning for Natural Language Processing in Room 2 in 5 minutes TRIGGER:-PT5M END:VALARM END:VEVENT BEGIN:VEVENT SUMMARY:Deep Learning for Computer Vision DTSTART:20160702T033000Z DTEND:20160702T053000Z DTSTAMP:20260421T165024Z UID:session/GwR2eo2MwvcwPu9uV7VAUj@hasgeek.com SEQUENCE:2 CATEGORIES:Workshop,Intermediate CREATED:20160620T175615Z DESCRIPTION:Some of the theory covered will be:\n\n1. From neurons to netw orks\, a full overview of the nuts and bolts.\n2. Types of networks\, from RBMs to CNNs to RNNs.\n3. How they are used in the world of CV. A discuss ion of what works and what doesn't.\n4. The fundamentals of training Deep Learning networks. \n5. On existing frameworks and using GPUs.\n\nA relati vely large number of potential projects will be available for the workshop \, and the participants will have access to AWS ec2 GPU instances for trai ning and testing.\nSome Potential workshop projects:\n\n1. Toy problems ex ploring the different architectures and relative merits.\n2. Real world cl assification problems solved with different architectures.\n3. Exploring n ovel and hybrid architectures (if time permits).\n\n### Speaker bio\n\nDr. Anand Chandrasekaran is a founder and the CTO of Mad Street Den\, an AI c ompany specializing in computer vision. In addition to an academic backgro und in the fields of neuroscience and neuromorphic engineering\, he has be en a member of teams working on DARPA projects in cognition and vision.\n LAST-MODIFIED:20230810T072606Z LOCATION:Room 1 - Google India Pvt. Ltd\nBengaluru\nIN ORGANIZER;CN="The Fifth Elephant":MAILTO:no-reply@hasgeek.com URL:https://hasgeek.com/fifthelephant/deep-learning-2016/schedule/deep-lea rning-for-computer-vision-GwR2eo2MwvcwPu9uV7VAUj BEGIN:VALARM ACTION:display DESCRIPTION:Deep Learning for Computer Vision in Room 1 in 5 minutes TRIGGER:-PT5M END:VALARM END:VEVENT BEGIN:VEVENT SUMMARY:Tea Break DTSTART:20160702T053000Z DTEND:20160702T054500Z DTSTAMP:20260421T165024Z UID:session/SXLX7RMgQH7DqzGvcfpycW@hasgeek.com SEQUENCE:0 CREATED:20160620T182608Z DESCRIPTION:\n LAST-MODIFIED:20160620T182632Z LOCATION:Bangalore ORGANIZER;CN="The Fifth Elephant":MAILTO:no-reply@hasgeek.com BEGIN:VALARM ACTION:display DESCRIPTION:Tea Break in 5 minutes TRIGGER:-PT5M END:VALARM END:VEVENT BEGIN:VEVENT SUMMARY:Deep Learning for Computer Vision contd. DTSTART:20160702T054500Z DTEND:20160702T074500Z DTSTAMP:20260421T165024Z UID:session/XkAY4DpxqJZLegHDp2Hbxd@hasgeek.com SEQUENCE:0 CREATED:20160620T182710Z DESCRIPTION:\n LAST-MODIFIED:20160630T111209Z LOCATION:Room 1 - Google India Pvt. Ltd\nBengaluru\nIN ORGANIZER;CN="The Fifth Elephant":MAILTO:no-reply@hasgeek.com BEGIN:VALARM ACTION:display DESCRIPTION:Deep Learning for Computer Vision contd. in Room 1 in 5 minute s TRIGGER:-PT5M END:VALARM END:VEVENT BEGIN:VEVENT SUMMARY:Introduction to Deep Learning for Natural Language Processing cont d. DTSTART:20160702T054500Z DTEND:20160702T071500Z DTSTAMP:20260421T165024Z UID:session/ASBiy76mKfkqggELiMebqN@hasgeek.com SEQUENCE:0 CREATED:20160620T182738Z DESCRIPTION:\n LAST-MODIFIED:20160629T133249Z LOCATION:Room 2 - Google India Pvt. Ltd\nBengaluru\nIN ORGANIZER;CN="The Fifth Elephant":MAILTO:no-reply@hasgeek.com BEGIN:VALARM ACTION:display DESCRIPTION:Introduction to Deep Learning for Natural Language Processing contd. in Room 2 in 5 minutes TRIGGER:-PT5M END:VALARM END:VEVENT BEGIN:VEVENT SUMMARY:Lunch DTSTART:20160702T071500Z DTEND:20160702T074500Z DTSTAMP:20260421T165024Z UID:session/RuaNWDiS8mvGiE9LFbZjW@hasgeek.com SEQUENCE:0 CREATED:20160701T100805Z DESCRIPTION:\n LAST-MODIFIED:20160701T100815Z LOCATION:Bangalore ORGANIZER;CN="The Fifth Elephant":MAILTO:no-reply@hasgeek.com BEGIN:VALARM ACTION:display DESCRIPTION:Lunch in 5 minutes TRIGGER:-PT5M END:VALARM END:VEVENT BEGIN:VEVENT SUMMARY:Lunch DTSTART:20160702T074500Z DTEND:20160702T084500Z DTSTAMP:20260421T165024Z UID:session/VZKCRj3FkSEjctdYdoHhkT@hasgeek.com SEQUENCE:0 CREATED:20160620T182813Z DESCRIPTION:\n LAST-MODIFIED:20160630T111214Z LOCATION:Bangalore ORGANIZER;CN="The Fifth Elephant":MAILTO:no-reply@hasgeek.com BEGIN:VALARM ACTION:display DESCRIPTION:Lunch in 5 minutes TRIGGER:-PT5M END:VALARM END:VEVENT END:VCALENDAR