Submissions

Anthill Inside 2017

On theory and concepts in Machine Learning, Deep Learning and Artificial Intelligence. Formerly Deep Learning Conf.

Accepting submissions

Not accepting submissions

Jaidev Deshpande

Understanding Neural Networks with Theano

Theano is not only a powerful tool to build and run deep and shallow neural networks, it is also a wonderful learning resource. Since it works primarily on symbolic mathematical expressions, it can help us understand how learning in neural networks can be interpreted in terms of equations, vectors, variables and Python functions. more
  • 2 comments
  • Rejected
  • 10 Apr 2017
Section: Workshop Technical level: Intermediate

Navin

Video thumbnail

Saving the Princess with Deep Learning

Deep Learning has provided an entirely new paradigm of solving problems which were otherwise deemed difficult to solve and is widely seen as a strong leap towards AGI. The field is moving at a rapid pace and innovative solutions to problems keep coming up every day. more
  • 1 comment
  • Confirmed & scheduled
  • 11 Apr 2017
Section: Crisp talk Technical level: Intermediate

Arthi Venkataraman

Video thumbnail

Deep learning for feature extraction from incident data

Lots of incident data is available in large corporate. However it is Noisy and inaccurate. Classification directly using TFIDF vectorization and machine learning models gives low accuracy. Lots of effort is spent in hand curation of data. Objective is to automatically extract features using deep learning techniques to get a higher lever representation of the text in the incidents. Downstream task… more
  • 4 comments
  • Under evaluation
  • 12 Apr 2017
Section: Crisp talk Technical level: Intermediate

Anuj Gupta

Learning representations of text for NLP

Think of your favorite NLP application that you wish to build - sentiment analysis, named entity recognition, machine translation, information extraction, summarization, recommender system, to name a few. A key step to building it is - using the right technique to represent the text in a form that machine can understand. In this workshop, we will understand key concepts, maths, and code behind st… more
  • 5 comments
  • Confirmed
  • 20 Apr 2017
Section: Workshop Technical level: Intermediate

Anil Hebbar

Introduction to Bounding Box Neural Networks

Neural Networks are rapidly gaining traction in applications such as autonomous vehicles, industrial automation and other verticals. Bounding box neural networks are fast emerging as preferred method for vision application where location accuracy, classification, speed of inference as well as minimal data size for transmission to controllers are all important. This talk aims to introduce concepts… more
  • 2 comments
  • Rejected
  • 24 Apr 2017
Section: Full talk Technical level: Intermediate

haridas n

Named Entity Recognition using DL methods

One of the main problems in NLP is the Named Entity Recognition(NER).The NER problems are addressed using traditional Machine Learning techniques, It mainly involves feature representation(Common step in all NLP problems), and then make use of a ML classifier to train and predict the correct Named Entity. The evolution of better feature representation methods and RNN based neural networks really … more
  • 1 comment
  • Cancelled
  • 25 Apr 2017
Section: Full talk Technical level: Intermediate

Abdul Muneer

Deep Learning with TensorFlow

TensorFlow is an open source software library for numerical computation using data flow graphs. Created by Google Brain, it was quickly adopted by the machine learning community after it was open sourced. Now it is adopted by industry pioneers like DeepMind at Google, OpenAI, IBM etc. and is fast becoming the go-to library for implementing deep neural networks. This workshop aims to cover the cor… more
  • 0 comments
  • Rejected
  • 26 Apr 2017
Section: Workshop Technical level: Intermediate

shashank gupta

Information Retrieval using Deep Learning

Neural networks are current state-of-the-art in almost all Computer Vision, Natural Language Processing and Speech tasks. Convolution Neural Networks, a deep learning model are go-to choice in Computer Vision. Similarly Recurrent Neural Networks (RNNs) are popular choice in NLP. The area of information retrieval is no different. Neural nets are slowly progressing towards becoming state-of-the-art… more
  • 2 comments
  • Rejected
  • 26 Apr 2017
Section: Full talk Technical level: Intermediate

Vidyasagar Nallapati

Malware Detection and Pattern Recognition using Deep Learning

Malware is a serious and evolving threat to security across corporates and governments, the research on malware detection using data mining, pattern recognition and machine learning methods had been there for a long time. Signature-based solutions, Heuristic techniques, Sandbox solutions have been in use and several frameworks are built around them however they are built on shallow learning archi… more
  • 2 comments
  • Rejected
  • 27 Apr 2017
Section: Crisp talk Technical level: Intermediate

Ananth Krishnamoorthy

KERAS: A Versatile Modeling Layer For Deep Learning

As practitioners in Deep Learning, we often want to understand emerging areas by prototyping and modeling. While there are many python libraries for deep learning, Keras stands out for it’s simplicity in modeling. more
  • 0 comments
  • Rejected
  • 27 Apr 2017
Section: Full talk Technical level: Intermediate

Kiran Vaidhya

Video thumbnail

Unsupervised and Semi-Supervised Deep Learning for Medical Imaging

Availability of labelled data for supervised learning is a major problem for narrow AI in current day industry. In imaging, the task of semantic segmentation (pixel-level labelling) requires humans to provide strong pixel-level annotations for millions of images and is difficult when compared to the task of generating weak image-level labels. Unsupervised representation learning along with semi-s… more
  • 1 comment
  • Confirmed & scheduled
  • 29 Apr 2017
Section: Full talk Technical level: Advanced

Ramanan Balakrishnan

Hitchhiker’s Guide to Generative Adversarial Networks (GANs)

Unsupervised learning has always been a tough problem to crack for researchers and practitioners. The last few years, however, have seen huge strides being made here with the widespread development of generative models, or specifically Generative Adversarial Networks (GANs). more
  • 5 comments
  • Confirmed & scheduled
  • 29 Apr 2017
Section: Full talk Technical level: Intermediate

Pallavi Ramicetty

Typography detection using Deep Convolutional Neural Networks

Keeping undesirable content out of social networks and communication channels is a common problem. Our email systems today have sophisticated “spam filters” thanks to which we’re protected from much harm and waste of time. The problem of spam is particularly harsh in niche social networks and interest groups which are small and sensitive to disruption. We run one such niche social network for typ… more
  • 4 comments
  • Rejected
  • 29 Apr 2017
Section: Crisp talk Technical level: Intermediate

Satish Palaniappan

Video thumbnail

Deep learning based OCR engine for the Indus script

Computational epigraphy is an interdisciplinary area that combines computing and the study of ancient inscriptions. The main challenge or bottleneck faced in the field of epigraphical research is the lack of standardized corpora of the ancient scripts under study. Preparing such data from raw archaeological records, requires laborious human effort, expertise and a lot of time. Machine Learning ha… more
  • 0 comments
  • Waitlisted
  • 30 Apr 2017
Section: Crisp talk Technical level: Intermediate

irfan basha sheik

Deep Type - deep convolutional neural networks for style transfer in typography

At Imaginea, we run a social network for typoholics called Fontli as our designers have a passion for the field. Folks share typography that they catch in the wild or work that they’ve created themselves. Members ask others for font identification and tips, and tag what they’re able to identify themselves. more
  • 0 comments
  • Rejected
  • 30 Apr 2017
Section: Full talk Technical level: Intermediate

Subramanya Mayya

Retail Loss Prevention based on Deep Learning

Items left on the bottom of the shopping cart during checkout is a major source of revenue loss to the retail industry. The Bottom of Basket (BoB) loss or shrinkage as it is called, runs into billions of dollars. Advanced computer vision technology can play an important role in preventing this loss. The presentation covers the design and implementation details of such a solution based on Deep Neu… more
  • 1 comment
  • Rejected
  • 30 Apr 2017
Section: Full talk Technical level: Intermediate

saurabh agarwal

Video thumbnail

Taming Convolution Neural Networks for Image Recognition

The talk is about CNN’s the poster-boys of Deep Learning. One of the most successful models which have given absolutely amazing results in image recognition tasks. The talk will first cover the basics of Convnet. Talk about the reasons why the world uses and what makes them great models for Image recognition. On the surface not much has changed in convolutional neural networks, but in last five y… more
  • 0 comments
  • Rejected
  • 30 Apr 2017
Section: Full talk Technical level: Intermediate

Sherin Thomas

PyTorch Demystified, Why Did I Switch

PyTorch entered into the realm of DL framework with the promise of being “Numpy on GPU”. The obvious failures of static graph implementation for certain use cases is increasing industry wide adoption of PyTorch. Dynamic Computation Graph being the backbone of PyTorch, comes with some perks. more
  • 3 comments
  • Confirmed & scheduled
  • 28 May 2017
Section: Full talk Technical level: Beginner

abhineet verma

Streaming video analytics using deep learning on large scale surveillance data @ Fractal Analytics

Video surveillance systems are increasingly becoming vital tools for protecting people and property. The increasing availability and lower cost of high-quality video cameras has increased the reach and the effectiveness of deploying and efficiently using video analytics systems. Even though video data often provides a very high amount of information, this data has not been efficiently used by ana… more
  • 2 comments
  • Rejected
  • 25 Apr 2017
Technical level: Advanced

Rajesh Gudikoti

Supervised-machine-learning without coding

We can build the machine learning model which can understand the linguistic nuances and relationships specific to a industry. Once model is trained and evaluated, you can use it to extract domain specific entities from new documents. more
  • 4 comments
  • Rejected
  • 07 Jun 2017
Section: Full talk Technical level: Beginner

Anuj Gupta

Synthetic Gradients – Decoupling Layers of a Neural Nets

Once in a while comes an (crazy!) idea that can change the very fundamentals of an area. In this talk we will see one such idea that can change how neural networks are trained. more
  • 0 comments
  • Confirmed & scheduled
  • 09 Jun 2017
Section: Full talk Technical level: Intermediate

Abhijeet Katte

Video thumbnail

The Importance of Knowing What We Don’t Know - Bayesianism and Deep Learning

Most deep learning models are often viewed as deterministic functions, seen as opaque and different from probabilistic models. But that is not fully true. The probabilistic view of machine learning offers confidence bounds for data analysis and decision making, information that a biologist for example would rely on to analyse her data, or an autonomous car would use to decide whether to take a tu… more
  • 2 comments
  • Rejected
  • 10 Jun 2017
Section: Crisp talk Technical level: Beginner

Konda Reddy Mopuri

Adversarial attacks on deep learning models

Recent researh efforts show that deep learning models are vulnerable to small but structured perturbations. This quasi-imperceptible noise can fool the state-of-the-art deep models (eg: object recognition CNNs) to infer wrong predictions. This noise is referred to as adversarial perturbation. It is shown that perturbation computed for one network is able to fool a new network trained with differe… more
  • 1 comment
  • Confirmed & scheduled
  • 10 Jun 2017
Section: Full talk Technical level: Intermediate

Shubham Dokania

Deep Learning Applications: A hands-on approach

Deep Learning, although a trending topic, appears as a challenging topic to beginners. There has been significant improvement in Deep Learning frameworks in the recent years, making it easier for everyone to hop-on the Machine Learning bandwagon. This workshop is aimed at giving participants a hands-on experience of a variety of deep learning techniques, while discussing about the underlying math… more
  • 5 comments
  • Awaiting details
  • 10 Jun 2017
Section: Workshop Technical level: Intermediate

Vasudev Singh

Highway Networks and ResNet : A deeper approach towards Deep Learning .

Deep Learning though termed so but as the network becomes deeper the neural networks are more difficult to train and their preformance also start to degrade. Residual learning framework(ResNet and Highway Networks) is an Newer kind of architecture which ease the training of networks that are substantially deeper than those used previously, helps overcome the degradation problem and lets the netwo… more
  • 0 comments
  • Rejected
  • 10 Jun 2017
Section: Full talk Technical level: Intermediate

Sachin Kumar

Decoding Neural Image Captioning

Humans have been captioning images involuntary since decades and now in the age of social media where every image have a caption over various social platforms. Psychologically those things are affected by events and scenarios running in mind or infulenced by nearby activities and emotion. Sometimes those are far-far away from real context. Describing the content of an image is a fundamental probl… more
  • 1 comment
  • Under evaluation
  • 10 Jun 2017
Section: Full talk Technical level: Intermediate

SATYAM SAXENA

Neural Stack: Augmenting Recurrent Neural Networks with Memory

Recurrent neural networks (RNNs) offer a compelling tool for processing natural language input in a straightforward sequential manner. Though they suffer from various limitations which do not allow them to easily model even the simple transduction tasks. In this talk, we will discuss new memory-based recurrent networks that implement continuously differentiable analogues of traditional data struc… more
  • 3 comments
  • Rejected
  • 11 Jun 2017
Section: Full talk Technical level: Intermediate

Sarath R Nair

From RNN to Attention

The motivation and ideas behind RNN to LSTM to Attention Mechanism and wind up with latest trends , along with mathematical ideas of Backpropogation . more
  • 3 comments
  • Rejected
  • 12 Jun 2017
Section: Full talk Technical level: Intermediate

Laksh Arora

Demystifying Visual Question Answering

We are witnessing a renewed excitement in multi-discipline Artificial Intelligence (AI) research problems. In particular, research in image and video captioning that combines Computer Vision (CV), Natural Language Processing (NLP), and Knowledge Representation & Reasoning (KR) has dramatically increased in the past year. Since the time, Alan Turing has developed Turing Test, it has become an impo… more
  • 2 comments
  • Rejected
  • 14 Jun 2017
Section: Full talk Technical level: Intermediate

Fariz Rahman

Keras: Deep Learning for Python

An introduction to the python deep learning library Keras, the philosophy behind Keras, building and training trivial as well as complex models such as GANs, RL, etc using Keras, deploying a Keras model in a production environment, and the future of Keras. Intended audience: Basic algebraic skills and python experience. more
  • 1 comment
  • Cancelled
  • 17 Jun 2017
Section: Full talk Technical level: Advanced

Gur Raunaq Singh

Making a Text-Summarizer with Keras

One of the common uses of Machine Learning in a lot of mobile applications is Text-Summarization. It is one of the key techniques companies are using for improving their products, or some even have complete mobile apps based on it (apps like Awesummly). more
  • 3 comments
  • Rejected
  • 19 Jun 2017
Section: Crisp talk Technical level: Intermediate

Ashish Mogha

Video thumbnail

Neural Machine Translation

Our thinking process is desinged such that multiple thoughts capture our minds at different point of time,therefore hampering our ability to recollect every thought from scratch.Our thoughts have persistence,traditional neural networks can’t do this, and it seems like a major shortcoming but recurrent neural networks address this issue. In the domain of NLP/Speech, RNNs transcribe speech to text,… more
  • 0 comments
  • Under evaluation
  • 20 Jun 2017
Section: Full talk Technical level: Intermediate

Satwik Kansal

Video thumbnail

Developing agents with Deep Reinforcement learning

Most of the people would have heard of Deepmind’s AI getiing really good at playing Atari games. more
  • 2 comments
  • Rejected
  • 20 Jun 2017
Section: Full talk Technical level: Beginner

saurabh agarwal Proposing

Practical Deep Learning

Understanding the nuts and bolts of a Deep Learning (DL) architecture has always been a tough ride for people with a not-so-mathematical background. The goal of the workshop is to get the participants to understand the practicalities to be considered while building deep networks such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) by using a hands-on approach, not nec… more
  • 0 comments
  • Confirmed
  • 22 Jun 2017
Section: Workshop Technical level: Intermediate

Chandrish M

Application Dependency Data Performance Mapping tool - Dynatrace

More companies today are adopting cloud services and related technologies like microservices architecture and containerization to build and deliver digital services faster and achieve greater IT agility. Monitoring and managing the performance of these dynamic application environments spanning the cloud and other third-party services is difficult, however, without the right tools. Leveraging an a… more
  • 0 comments
  • Rejected
  • 22 Jun 2017
Section: Crisp talk Technical level: Beginner

sainath v

Leonardo Machine Learning Foundation - Adding Intelligence to your Enterprise Business

Machine learning and the larger world of artificial intelligence (AI) are no longer martial arts. As a new breed of software that is able to learn without being explicitly programmed, machine learning (deep learning and supervised learning) can access, analyse, and find patterns in, Big Data in a way that is beyond human capabilities. We all know that the world is moving to a more data driven dec… more
  • 0 comments
  • Under evaluation
  • 22 Jun 2017
Section: Crisp talk Technical level: Beginner

Malaikannan Sankarasubbu

Video thumbnail

CNN for NLP

CNN is typically used for Computer Vision, but it can be applied for wide variety of NLP Problems. This talk will cover fundamentals of Convolutional Neural Networks, how to apply it for NLP and then a Keras/PyTorch Implementation for it. more
  • 1 comment
  • Under evaluation
  • 24 Jun 2017
Section: Full talk Technical level: Intermediate

Kumar Shubham

Video thumbnail

Augmenting Solr’s NLP Capabilities with Deep-Learning Features to Match Images

Matching images with human-like accuracy is typically extremely expensive. A lot of GPU resources and training data are required for the deep-learning model to perform image-matching. While GPU is something that most companies can afford, training data is hard to obtain. more
  • 0 comments
  • Under evaluation
  • 28 Jun 2017
Section: Crisp talk Technical level: Intermediate

Aman Neelapa

Deep learning with limited data

When working on a domain specific problem, it’s often impossible to find large datasets to build right sized models. However models trained on one task capture relations in the data which can easily be reused for different problems in the same domain. Recent advances in transfer learning and few shot learning demonstrate the ability of deep networks to assimilate new data without falling prey to … more
  • 0 comments
  • Cancelled
  • 05 Jul 2017
Section: Crisp talk Technical level: Intermediate

Amar Lalwani

How Deep is Deep Learning?

Undoubtedly Deep Learning is a recent significant step towards Artificial General Intelligence because of its sheer ability to learn most complex tasks. Deep Learning has been shown to achieve spectacular results in almost all domains. But as expected, there is always a price to pay for everything, especially for better things. And here the price is the interpretability and simplicity. Moreover, … more
  • 0 comments
  • Confirmed & scheduled
  • 09 Jul 2017
Section: Crisp talk Technical level: Intermediate

Gaurav Goswami

Getting Started with GPU Accelerated Deep Learning

Deep learning has been applied to various domains with great success and is a popular technique to solve challenging machine learning problems in the real world. However, deep learning is also computationally expensive and it is not feasible to train a deep network in a reasonable time frame on large databases without using GPU acceleration. In this talk, I will provide a tutorial on how to setup… more
  • 2 comments
  • Under evaluation
  • 10 Jul 2017
Section: Crisp talk Technical level: Beginner

Arnab Biswas

Video thumbnail

Identifying Urban Makeshift Communities using satellite imagery and geo-coded data

The aim of this talk is to provide a comprehensive description of the experimentation & explorations done by DataKind-Bangalore to identify non-permanent urban poor communities in Bangalore using Machine Learning (Transfer learning) with satellite imagery and geo-coded data for Pollinate Energy. more
  • 2 comments
  • Confirmed & scheduled
  • 10 Jul 2017
Section: Crisp talk Technical level: Intermediate

Praveen Sridhar

Video thumbnail

Keep Calm and Trust your Model - On Explainability of Machine Learning Models

The accuracy of Machine Learning models is going up by the day with advances in Deep Learning. But this comes at a cost of explainability of these models. There is a need to uncover these black boxes for the Business users. This is very essential especially for heavily regulated industries like Finance, Medicine, Defence and the likes more
  • 1 comment
  • Confirmed & scheduled
  • 10 Jul 2017
Section: Full talk Technical level: Intermediate

Vijay Ramakrishnan

Deep Learning approaches for Named Entity Recognition

Using a Bi-Directional LSTM network we were able to achieve state of the art accuracies on Named Entity Data on WNUT 2016 Twitter Noisy data. more
  • 2 comments
  • Under evaluation
  • 13 Jul 2017
Section: Crisp talk Technical level: Intermediate

Vijay Gabale

Panel on product and AI

Basis for the discussion: Technology is getting commoditized rapidly. Google, FB are on open source spree that solves hard problems. However, there is still scope to build vertical specific AI products. more
  • 0 comments
  • Confirmed & scheduled
  • 14 Jul 2017
Section: Birds of a Feather (BOF) session Technical level: Beginner

Rebanta Dutta Proposing

AI: Unleashing the next wave

This talk provides with a high-level overview of Intel’s Artificial Intelligence (AI) vision and product portfolios. This talks starts with where Intel sees opportunity in various verticals and industries for AI and we will take one example of Intel’s comprehensive AI strategy in action. This talk gives overview on both hardware, software portfolio and also our developer outreach programs and eng… more
  • 0 comments
  • Confirmed & scheduled
  • 17 Jul 2017
Section: Full talk Technical level: Intermediate

Mukesh Gangadhar

AI on IA

The presentation will provide an overview of hardware and software products for Deep learning, covering an overview of Intel software tools meant for artificial intelligence, how developers can get access to these tools. The talk will also share details about Intel’s software optimization efforts to improve the performance of deep learning frameworks on Intel® architecture. more
  • 0 comments
  • Confirmed & scheduled
  • 18 Jul 2017
Section: Workshop Technical level: Intermediate

Saad Nasser

AI in self driving vehicles - a practitioner's perspective

Ati Motors is creating an autonomous cargo vehicle, and uses machine learning extensively in its autonomy stack - from perception, object detection and tracking, to driving policy. The talk will take a breadth first approach to the problem space rather than focusing on any one particular area. The objective is to familiarise the audience with the range of real life applications within a single pr… more
  • 0 comments
  • Confirmed & scheduled
  • 22 Jul 2017
Section: Full talk Technical level: Beginner

Girish Patil

Apache MXNet, a highly memory efficient deep learning framework

GPU memory is the most expensive deep learning resource. MXNet was designed to allow complex deep learning with most minimal requirements on GPU memory. This allows for training of complex models with accessible chips. This session will discuss how MXNet achieves low memory footprint, as well as other useful features of this rapidly emerging framework. more
  • 0 comments
  • Confirmed & scheduled
  • 22 Jul 2017
Section: Crisp talk Technical level: Intermediate

Sandhya Ramesh Proposing

OTR - DL and image

Off The Record Session on DL and image. Outline The OTR will have participants from the field leading these discussions. more
  • 0 comments
  • Confirmed & scheduled
  • 22 Jul 2017
Section: Full talk Technical level: Beginner

Vikas Raykar Proposing

Deep Reinforcement Learning : A tutorial

Reinforcement Learning (RL) is a natural computational paradigm for agents learning from interaction to achieve a goal. Deep learning (DL) provides a powerful general-purpose representation learning framework. A combination of these two has recently emerged as a strong contender for artificial general intelligence. This tutorial will povide a gentle exposition of RL concepts and DL based RL with … more
  • 0 comments
  • Confirmed
  • 25 Jul 2017
Section: Full talk Technical level: Beginner

Hosted by

Anthill Inside is a forum for conversations about risk mitigation and governance in Artificial Intelligence and Deep Learning. AI developers, researchers, startup founders, ethicists, and AI enthusiasts are encouraged to: more