Accepting submissions
Not accepting submissions
Nischal HP Introduction to Deep Learning for Natural Language ProcessingThis workshop will provide an introduction to deep learning for natural language processing (NLP). It will cover some of the common deep learning architectures, describe advantages and concerns, and provide hands-on experience. more
Section: Workshop
Technical level: Intermediate
|
|
pr
pradyumna reddy Residual Learning and Stochastic Depth in Deep Neural NetworksThe talk will introduce Deep Residual Learning and provide an in depth idea of how Residual Networks work. It will also cover stochastic depth method which helps to increase the depth of residual networks beyond 1200 layers. more
Section: Crisp talk
Technical level: Intermediate
|
|
AJ
Arjun Jain Joint Training of a Convolutional Network and a Graphical Model for Human Pose EstimationWe propose a new hybrid architecture that consists of a deep Convolutional Network and a Markov Random Field. We show how this architecture is successfully applied to the challenging problem of articulated human pose estimation in monocular images. The architecture can exploit structural domain constraints such as geometric relationships between body joint locations. We show that joint training o… more
Section: Crisp talk
Technical level: Advanced
|
Anuj Gupta Proposing Debugging DeepNets - practitioners black bookSecret Sauce to Building production quality Deep Nets more
Section: Full talk
Technical level: Advanced
|
|
AB
Aakanksha Bapna Automated Interior Designing using Bayesian networksI’ll be presenting about an almost completely automated intelligent system that produces realistic and aesthetically appealing interior designs for homes. The particularly striking feature of our system is that it generates multiple plausible options for an empty room. The relationships between different elements of a room and items placed in the room are represented as Bayesian networks. The cau… more
Section: Crisp talk
Technical level: Intermediate
|
|
AC
Anand Chandrasekaran Deep learning: A convoluted overview with recurrent themes and beliefs.The data needed to represent the world around is daunting. But somehow, we need to capture a lot of that information explicitly or implicitly to create ‘intelligent’ machines. It was formerly believed that explicitly capturing all this information would give rise to Artificial Intelligence through clever programming. But with every passing decade, despite the rise in computational power, this onl… more
Section: Full talk
Technical level: Intermediate
|
|
VG
Vijay Gabale Deep Dive Into Building Chat-bots Using Deep LearningThere has been growing interest on shedding boring and cumbersome “search and get thousand results” interface to move towards a “conversational” interface to ease the reception of deluge of information in various web and mobile applications. While a naive search bar that simplified information extraction and delivery of web pages was the rage in early 2000s, exponential increase in data and infor… more
Section: Full talk
Technical level: Intermediate
|
|
AN
Abhishek Narain Events Build Build 2016 Microsoft Cognitive Services: Build smarter and more engaging experiencesWith Microsoft’s Cognitive Services, you can build smarter and more engaging experiences that bring the knowledge of the web right into the experience, while interacting with users in a natural way, and across multiple languages. In this session, we will show how the capabilities of these intelligent services can be integrated into your experiences with just a few lines of code, so your users can… more
Section: Full talk
Technical level: Beginner
|
|
Anuj Gupta Activations, Objectives and Optimisers - Nuts & Bolts of a DeepNetBuilding a good Deep Network is not an easy task. From the architecture of the network to various parameters - each choice is very crucial as it has a huge bearing on the performance (both accuracy and efficiency) of the DeepNet. Of these, three important component any practitioner must choose are : which Activation function, Loss/Objective Function and Optimiser to use ? more
Section: Full talk
Technical level: Intermediate
|
|
Anuj Gupta Building DeepNets using KerasIn todays world many ML teams have started to look towards DeepNets as potential models to build intelligent system. While DeepNets hold lot of promise, building them from scratch can be very time consuming. What is needed is elaborate library that will facilitate quick experimentation. Thats where Keras comes handy. Its moto is - “Being able to go from idea to result with the least possible dela… more
Section: Workshop
Technical level: Intermediate
|
|
SV
Suthirth Vaidya Challenges & Implications of Deep Learning in HealthcareDeep Learning has made leaps and bounds in several industries around us – products ranging from self-driving cars, voice assistants, fashion recognition engines and enterprise bots are no longer science fiction ideas. Despite the advances in several industries, intelligence in healthcare has seen limited penetration. Other than the giants of IBM, few have taken up building intelligent healthcare … more
Section: Full talk
Technical level: Intermediate
|
|
SJ
Sunita John Deep Learning with MATLAB : Real-time Object Recognition and Transfer LearningDeep learning is now within reach for anyone to use! We will explore real-world applications of deep learning by showing demos of transfer learning and real-time object recognition. Deep learning models can be difficult to train, evaluate and compare. In this session we will explore how MATLAB addresses the most common challenges such as handling large sets of images and retraining existing netwo… more
Section: Crisp talk
Technical level: Intermediate
|
|
RM
Rajarshee Mitra Sequence learningThe proposed talk aims to provide a thorough explanation of language modelling (word and sentence embeddings), application of RNN, LSTMs to text - predicting text, mapping sentence to sentence, chatbots. more
Section: Full talk
Technical level: Intermediate
|
|
VG
Vivek Gandhi Debugging deep netsDeep learning networks are typically large neural networks with very complex designs containing millions of neurons . The number of parameters to be learned in case of these networks is huge. Finding the right set of parameters is a non-trivial task and requires good amount of experience. You can run into all sort of problems such as exploding gradients, infinite losses, overfitting etc. In this … more
Section: Full talk
Technical level: Intermediate
|
|
AT
Abhishek Thakur Applied Deep LearningThis talk gives an overview of current advancements in the field of deep learning and neural networks and explains how neural networks can be implemented and used for most of the machine learning problems. more
Section: Full talk
Technical level: Intermediate
|
|
HJ
Hemant Jain Deep learning for Image and Feature recognitionWith the rapid increase in images in social media and smarter devices, there is a tremendous amount of information waiting to be tapped into. Deep learning’s design makes it a very useful tool in today’s world. Extracting the right features after necessary pre-processing of images is often challenging. This talk will cover important hacks on how to deal with images, transform and extract features… more
Section: Full talk
Technical level: Intermediate
|
|
AK
Ashish Kumar Text made Understandable by MachinesUnderstanding language is a trivial task for humans, but when it comes to mimic that task by machines it doesn’t remain that trivial. For humans, everything(image, text, speech etc.) is in terms for electrical impulses. In the same way for machines, everything is numbers either in the vector form (in the case of text or speech) or matrix form (in the case of images or videos). Deep learning has r… more
Section: Full talk
Technical level: Intermediate
|
|
SS
Suraj Srinivas Making Deep Neural Networks smaller and fasterDeep neural networks with millions of parameters are at the heart of many state of the art machine learning models today. However, is has been shown that models with much smaller number of parameters can also perform just as well. A smaller model has the advantage of being faster to evaluate and easier to store - both of which are crucial for real-time and embedded / mobile applications. In this … more
Section: Crisp talk
Technical level: Intermediate
|
|
NS
Nishant Sinha Slot-Filling in Conversations with Deep LearningBuilding conversational assistants which help users get jobs done, e.g., order food, book tickets or buy phones, is a complex task. Your bot needs to understand ambiguous natural language inputs, guess user’s intent and context, extract relevant entities, lookup catalogs, generate responses to elicit more information, build user’s profile and finally create and fulfill orders!! While deep learnin… more
Section: Crisp talk
Technical level: Intermediate
|
|
SN
Sundara R Nagalingam Recent advancements in Deep Learning techniques using GPUs.NVIDIA has for long been a pioneer in providing the tools to facilitate deep learning. At the heart of deep learning lies the need to train Deep Neural Networks and then have these DNNs perform complex compute tasks in the shortest possible time. NVIDIA has made huge advances in developing a comprehensive software development kit, aimed at helping developers train DNNs at speeds that keep beating… more
Section: Sponsored talk
Technical level: Intermediate
|
|
KS
Koustubh Sinhal Object Detection using deep convolutional networkThe talk aims to cover the advancements in object detection framework based on convolutional networks. The goal of object category detection is to identify and localize objects of a given type in an image. The main challenge associated with object detection in unconstrained images is to localize the object regardless of its location and scale. I will cover various state of the art methods employe… more
Section: Crisp talk
Technical level: Advanced
|
|
NK
Neeraj Kumar Deep learning for computational pathologyWe strongly believe that the future of not only medical detection and diagnosis but also prognosis and treatment planning will be strongly influenced by pattern recognition and data analysis. Medical imaging will be no different, especially with the advent of techniques such as unsupervised feature extraction and deep learning aided by high performance computing (HPC) in the form of cloud cluster… more
Section: Full talk
Technical level: Intermediate
|
|
AV
Arthi Venkataraman Practical Deep LearningThis session will equip users with knowledge on Deep Learning. At end of session audience should have sufficient knowledge of deep learning networks, where they can be applied and what are the benefits of using the same. They will also get some practical tips on implementing these algorithms. An overview of how we build a a Text classifier using deep learning approach will be given. Results obtai… more
Technical level: Intermediate
|
|
AC
Anand Chandrasekaran Deep Learning for Computer VisionOne of the fields that have benefited the most from the rise of Deep Learning has been Computer Vision. The goal of this workshop is to have participants go from the basics to tackling a problem that might solve a real world problem. more
Section: Workshop
Technical level: Intermediate
|
|
JD
Jaley Dholakiya  Expresso - A user-friendly tool for Deep LearningWith a view to provide a user-friendly interface for designing, training and developing deep learning frameworks, we have developed Expresso, a GUI tool written in Python. Expresso is built atop Caffe, the open-source, prize-winning framework popularly used to develop Convolutional Neural Networks. Expresso provides a convenient wizard-like graphical interface which guides the user through variou… more
Section: Crisp talk
Technical level: Beginner
|