Anthill Inside 2017
On theory and concepts in Machine Learning, Deep Learning and Artificial Intelligence. Formerly Deep Learning Conf.
##About AnthillInside:
In 2016, The Fifth Elephant branched into a separate conference on Deep Learning. Anthill Inside is the new avataar of the Deep Learning conference.
Anthill Inside attempts to bridge the gap bringing theoretical advances closer to functioning reality.
Proposals are invited for full length talks, crisp talks and poster/demo sessions in the area of ML+DL. The talks need to focus on the techniques used, and may be presented independent of the domain wherein they are applied.
We also invite talks on novel applications of ML+DL, and methods of realising the same in hardware/software.
Case studies of how DL and ML have been applied in different domains will continue to be discussed at The Fifth Elephant.
https://anthillinside.in/2017/
Topics: we are looking for talks covering the following:
- Machine Learning with end-to-end application
- Deep Learning
- Artificial Intelligence
- Hardware / software implementations of advanced Machine Learning and Deep Learning
- IoT and Deep Learning
- Operations research and Machine Learning
##Format:
Anthill Inside is a two-track conference:
- Talks in the main auditorium and hall 2.
- Birds of Feather (BOF) sessions in expo area.
We are inviting proposals for:
- Full-length 40-minute talks.
- Crisp 15-minute how-to talks or introduction to a new technology.
- Sponsored sessions, of 15 minutes and 40 minutes duration (limited slots available; subject to editorial scrutiny and approval).
- Hands-on workshop sessions of 3 and 6 hour duration where participants follow instructors on their laptops.
- Birds of Feather (BOF) sessions.
You must submit the following details along with your proposal, or within 10 days of submission:
- Draft slides, mind map or a textual description detailing the structure and content of your talk.
- Link to a self-record, two-minute preview video, where you explain what your talk is about, and the key takeaways for participants. This preview video helps conference editors understand the lucidity of your thoughts and how invested you are in presenting insights beyond your use case. Please note that the preview video should be submitted irrespective of whether you have spoken at past editions of The Fifth Elephant or last year at Deep Learning.
- If you submit a workshop proposal, you must specify the target audience for your workshop; duration; number of participants you can accommodate; pre-requisites for the workshop; link to GitHub repositories and documents showing the full workshop plan.
##Selection Process:
- Proposals will be filtered and shortlisted by an Editorial Panel.
- Proposers, editors and community members must respond to comments as openly as possible so that the selection processs is transparent.
- Proposers are also encouraged to vote and comment on other proposals submitted here.
We expect you to submit an outline of your proposed talk, either in the form of a mind map or a text document or draft slides within two weeks of submitting your proposal to start evaluating your proposal.
You can check back on this page for the status of your proposal. We will notify you if we either move your proposal to the next round or if we reject it. Selected speakers must participate in one or two rounds of rehearsals before the conference. This is mandatory and helps you to prepare well for the conference.
A speaker is NOT confirmed a slot unless we explicitly mention so in an email or over any other medium of communication.
There is only one speaker per session. Entry is free for selected speakers.
We might contact you to ask if you’d like to repost your content on the official conference blog.
##Travel Grants:
Partial or full grants, covering travel and accomodation are made available to speakers delivering full sessions (40 minutes) and workshops. Grants are limited, and are given in the order of preference to students, women, persons of non-binary genders, and speakers from Asia and Africa.
##Commitment to Open Source:
We believe in open source as the binding force of our community. If you are describing a codebase for developers to work with, we’d like for it to be available under a permissive open source licence. If your software is commercially licensed or available under a combination of commercial and restrictive open source licences (such as the various forms of the GPL), you should consider picking up a sponsorship. We recognise that there are valid reasons for commercial licensing, but ask that you support the conference in return for giving you an audience. Your session will be marked on the schedule as a “sponsored session”.
##Important Dates:
- Deadline for submitting proposals: July 10
- First draft of the coference schedule: July 15
- Tutorial and workshop announcements: June 30
- Final conference schedule: July 20
- Conference date: July 30
##Contact:
For more information about speaking proposals, tickets and sponsorships, contact info@hasgeek.com or call +91-7676332020.
Please note, we will not evaluate proposals that do not have a slide deck and a video in them.
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
Accepting submissions
Not accepting submissions
|
JD
Jaidev Deshpande Understanding Neural Networks with TheanoTheano 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
Section: Workshop
Technical level: Intermediate
|
|
N
Navin  Saving the Princess with Deep LearningDeep 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
Section: Crisp talk
Technical level: Intermediate
|
|
AV
Arthi Venkataraman  Deep learning for feature extraction from incident dataLots 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
Section: Crisp talk
Technical level: Intermediate
|
|
AG
Anuj Gupta Learning representations of text for NLPThink 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
Section: Workshop
Technical level: Intermediate
|
|
AH
Anil Hebbar Introduction to Bounding Box Neural NetworksNeural 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
Section: Full talk
Technical level: Intermediate
|
|
hn
haridas n Named Entity Recognition using DL methodsOne 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
Section: Full talk
Technical level: Intermediate
|
|
AM
Abdul Muneer Deep Learning with TensorFlowTensorFlow 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
Section: Workshop
Technical level: Intermediate
|
|
sg
shashank gupta Information Retrieval using Deep LearningNeural 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
Section: Full talk
Technical level: Intermediate
|
|
VN
Vidyasagar Nallapati Malware Detection and Pattern Recognition using Deep LearningMalware 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
Section: Crisp talk
Technical level: Intermediate
|
|
AK
Ananth Krishnamoorthy KERAS: A Versatile Modeling Layer For Deep LearningAs 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
Section: Full talk
Technical level: Intermediate
|
|
KV
Kiran Vaidhya  Unsupervised and Semi-Supervised Deep Learning for Medical ImagingAvailability 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
Section: Full talk
Technical level: Advanced
|
|
RB
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
Section: Full talk
Technical level: Intermediate
|
|
PR
Pallavi Ramicetty Typography detection using Deep Convolutional Neural NetworksKeeping 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
Section: Crisp talk
Technical level: Intermediate
|
|
SP
Satish Palaniappan  Deep learning based OCR engine for the Indus scriptComputational 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
Section: Crisp talk
Technical level: Intermediate
|
|
is
irfan basha sheik Deep Type - deep convolutional neural networks for style transfer in typographyAt 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
Section: Full talk
Technical level: Intermediate
|
|
SM
Subramanya Mayya Retail Loss Prevention based on Deep LearningItems 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
Section: Full talk
Technical level: Intermediate
|
|
sa
saurabh agarwal  Taming Convolution Neural Networks for Image RecognitionThe 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
Section: Full talk
Technical level: Intermediate
|
|
ST
Sherin Thomas PyTorch Demystified, Why Did I SwitchPyTorch 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
Section: Full talk
Technical level: Beginner
|
|
av
abhineet verma Streaming video analytics using deep learning on large scale surveillance data @ Fractal AnalyticsVideo 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
Technical level: Advanced
|
|
AL
Akbar Ladak Object Classification in 3D: Working with LiDAR point cloudsLiDAR sensors are rapidly becoming mainstream not just to detect obstacles (as in self driving cars), but also to identify object classes for mapping, disaster relief and other use cases. more
Section: Crisp talk
Technical level: Intermediate
|
|
RG
Rajesh Gudikoti Supervised-machine-learning without codingWe 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
Section: Full talk
Technical level: Beginner
|
|
AG
Anuj Gupta Synthetic Gradients – Decoupling Layers of a Neural NetsOnce 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
Section: Full talk
Technical level: Intermediate
|
|
AK
Abhijeet Katte  The Importance of Knowing What We Don’t Know - Bayesianism and Deep LearningMost 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
Section: Crisp talk
Technical level: Beginner
|
|
KM
Konda Reddy Mopuri Adversarial attacks on deep learning modelsRecent 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
Section: Full talk
Technical level: Intermediate
|
|
SD
Shubham Dokania Deep Learning Applications: A hands-on approachDeep 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
Section: Workshop
Technical level: Intermediate
|
|
VS
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
Section: Full talk
Technical level: Intermediate
|
|
SK
Sachin Kumar Decoding Neural Image CaptioningHumans 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
Section: Full talk
Technical level: Intermediate
|
|
SS
SATYAM SAXENA Neural Stack: Augmenting Recurrent Neural Networks with MemoryRecurrent 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
Section: Full talk
Technical level: Intermediate
|
|
SN
Sarath R Nair From RNN to AttentionThe motivation and ideas behind RNN to LSTM to Attention Mechanism and wind up with latest trends , along with mathematical ideas of Backpropogation . more
Section: Full talk
Technical level: Intermediate
|
|
LA
Laksh Arora Demystifying Visual Question AnsweringWe 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
Section: Full talk
Technical level: Intermediate
|
|
FR
Fariz Rahman Keras: Deep Learning for PythonAn 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
Section: Full talk
Technical level: Advanced
|
|
GS
Gur Raunaq Singh Making a Text-Summarizer with KerasOne 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
Section: Crisp talk
Technical level: Intermediate
|
|
AM
Ashish Mogha  Neural Machine TranslationOur 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
Section: Full talk
Technical level: Intermediate
|
|
SK
Satwik Kansal  Developing agents with Deep Reinforcement learningMost of the people would have heard of Deepmind’s AI getiing really good at playing Atari games. more
Section: Full talk
Technical level: Beginner
|
|
sa
saurabh agarwal Proposing Practical Deep LearningUnderstanding 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
Section: Workshop
Technical level: Intermediate
|
|
CM
Chandrish M Application Dependency Data Performance Mapping tool - DynatraceMore 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
Section: Crisp talk
Technical level: Beginner
|
|
sv
sainath v Leonardo Machine Learning Foundation - Adding Intelligence to your Enterprise BusinessMachine 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
Section: Crisp talk
Technical level: Beginner
|
|
MS
Malaikannan Sankarasubbu  CNN for NLPCNN 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
Section: Full talk
Technical level: Intermediate
|
|
KS
Kumar Shubham  Augmenting Solr’s NLP Capabilities with Deep-Learning Features to Match ImagesMatching 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
Section: Crisp talk
Technical level: Intermediate
|
|
AN
Aman Neelapa Deep learning with limited dataWhen 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
Section: Crisp talk
Technical level: Intermediate
|
|
AL
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
Section: Crisp talk
Technical level: Intermediate
|
|
GG
Gaurav Goswami Getting Started with GPU Accelerated Deep LearningDeep 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
Section: Crisp talk
Technical level: Beginner
|
|
AB
Arnab Biswas  Identifying Urban Makeshift Communities using satellite imagery and geo-coded dataThe 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
Section: Crisp talk
Technical level: Intermediate
|
|
PS
Praveen Sridhar  Keep Calm and Trust your Model - On Explainability of Machine Learning ModelsThe 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
Section: Full talk
Technical level: Intermediate
|
|
VR
Vijay Ramakrishnan Deep Learning approaches for Named Entity RecognitionUsing 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
Section: Crisp talk
Technical level: Intermediate
|
|
VG
Vijay Gabale Panel on product and AIBasis 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
Section: Birds of a Feather (BOF) session
Technical level: Beginner
|
|
RD
Rebanta Dutta Proposing AI: Unleashing the next waveThis 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
Section: Full talk
Technical level: Intermediate
|
|
MG
Mukesh Gangadhar AI on IAThe 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
Section: Workshop
Technical level: Intermediate
|
|
SN
Saad Nasser AI in self driving vehicles - a practitioner's perspectiveAti 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
Section: Full talk
Technical level: Beginner
|
|
GP
Girish Patil Apache MXNet, a highly memory efficient deep learning frameworkGPU 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
Section: Crisp talk
Technical level: Intermediate
|
|
SR
Sandhya Ramesh Proposing OTR - DL and imageOff The Record Session on DL and image. Outline The OTR will have participants from the field leading these discussions. more
Section: Full talk
Technical level: Beginner
|
|
VR
Vikas Raykar Proposing Deep Reinforcement Learning : A tutorialReinforcement 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
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