ODSC India 2018
2018-08-31..2018-09-01
Bengaluru, India
| title | author | length |
|---|---|---|
| Keynote: Life Science Research at Scale | Denis C. Bauer | 46m |
Shows how VariantSpark random forest runs on Spark to analyze 22,000 genomes (≈80 million variant columns, a 1.7 trillion‑cell matrix) to surface… | ||
| The Deep Learning Revolution in Automatic Speech Recognition | Ananth Sankar | 45m |
Describes how speech systems move from GMM-HMM acoustic models to shared-parameter deep neural networks trained discriminatively, enabled by GPUs, producing a… | ||
| Q n A with Dr Tom Starke | Sheamus McGovern | 07m |
Claims that fully autonomous trading is ready are false; research shows progress on narrow signals but not end-to-end AI trading because markets contain heavy… | ||
| Q n A with Dr Ananth Sankar | Harish Kashyap K | 08m |
2005 single-author Nuance paper demonstrates system combination that measurably improves recognition accuracy; recent deep learning work drives word error… | ||
| Q n A with Dr Arun Verma | Sheamus McGovern | 08m |
Bloomberg uses an in-house annotated corpus of news and expert labels to train NLP models that produce real-time sentiment scoring for entities, feeding… | ||
| Q n A with Sohan Maheshwar | Sheamus McGovern | 06m |
This is a short QnA with Sohan Maheshwar at first #ODSC_India.
Here he talks about techniques in speech recognition like Hypothesis re-ranker, RNN and… | ||
| Q n A with Dr Denis Bauer | Sheamus McGovern | 08m |
Genomics generates a three billion-letter reference and is on track for 50% sequenced by 2025, producing roughly 20 exabytes per year, so traditional… | ||
| Conversational Agents at Scale: Retrieval and Generative approaches | Swapan Rajdev | 41m |
Compares a retrieval-based dialogue management pipeline (intent/entity slots, controlled replies, fast <2s responses, ~150 retrains/day) with a… | ||
| Keynote: Seeking Order amidst Chaos and Uncertainty | Ravi Mehrotra | 45m |
Shows how revenue management and dynamic pricing models succeed only when they forecast uncertainty not just point estimates and exploit real‑world structure… | ||
| Q n A with Drs Tarry Singh | Sheamus McGovern | 07m |
DeepKapha frames its work as improving deep learning research into deployable systems, claiming prototype frameworks that are automated and flexible and that… | ||
| Analytics & Science for Customer Experience in E-commerce | Dr Ravi, Dr Sidharth | 21m |
Flipkart builds SKU-level price intelligence for ~80 million products and ~150 million users, modeling demand with random forests/SVMs and unobserved component… | ||
| Auditory Intelligence : beyond speech recognition | Naoya Takahashi | 45m |
Proposes concrete systems: an unsupervised speech model that jointly learns subword units and a dictionary and outperforms phoneme-based systems, finding 384… | ||
| Puzzling Together a TeacherBot: ML, NLP, Active Learning & MicroServ | Vincenzo Tursi | 30m |
A TeacherBot named Emil maps KNIME forum questions to tutorial links using KNIME workflows and microservices, trained on ~5,000 forum posts and ~400 resources… | ||
| Detection & Classification of Fake news using Convolutional Neural Nets | Venkat J | 19m |
The proliferation of fake news or rumours in traditional news media sites, social media, feeds, and blogs have made it extremely difficult and challenging to… | ||
| It's All in the Data: The ML Behind Alexa's AI Systems | Sohan Maheshwar | 39m |
Alexa runs a cloud pipeline: wake‑word detection on device, ASR, NLU, skill selection and TTS, and hardware stays current because models update in the cloud… | ||
| Intelligent Autonomous Trading Systems - Are We There Yet? | Tom Starke | 37m |
Argues that fully autonomous, set-and-forget trading is not yet practical and gives concrete successes and limits: satellite imaging for crop acreage car… | ||
| Time Series Analysis of District-wise Government Spending in India | Gaurav Godhwani | 01h 03m |
About District Treasuries: District Treasuries are the nodal offices for all financial transactions of the Government within the district, managing both… | ||
| Deep Learning in Medical Image Diagnostics | Mahesh Balaji | 55m |
Convolutional CNN systems are applied to two pilots: a breast cancer pipeline that tiles whole‑slide images into patches, performs nuclei segmentation and… | ||
| Panel: Unanswered Questions - Ask the Experts! | Naresh Jain, Dr. Arun Verma, Denis C. Bauer, Favio Vázquez, Sheamus McGovern, Drs. Tarry Singh, Tom Starke, Veena Mendiratta | 01h 10m |
Fishbowl panel format with an empty chair invites audience experts to join; debate centers on hype versus reality in data science and AI, with repeated claims… | ||
| Social n/w Analytics to enhance Marketing Outcomes in Telecom Sector | Kavita Dwivedi | 28m |
This talk will focus on How SNA can help enhance the outcomes of Marketing Campaigns by using social network graphs .
Social network analytics (SNA) is the… | ||
| AR-MDN for e-Retail Demand Forecasting | Atin Ghosh | 38m |
AR-MDN combines feature embeddings, an MLP front end and LSTM recurrent layers to output probabilistic forecasts as a learned mixture density (Gaussian… | ||
| When the Art of Entertainment ties the knot with Science | Ujjyaini Mitra | 27m |
Builds AI models that predict a screenplay’s success probability and recommended production spend and casting tradeoffs, uses Microsoft/Google/Amazon video… | ||
| Machine Learning for medical rehabilitation | Praveen Srivatsa | 47m |
Walking is one of the most common human activity. But the human gait varies by gender, age, culture etc. How can we use pre-trained models to identify human… | ||
| ML and DL in Production: Differences and Similarities | Dakshinamurthy V Kolluru | 48m |
While architecting a data-based solution, one needs to approach the problem differently depending on the specific strategy being adopted. In traditional… | ||
| Recognition and Localization of Parking Signs using Deep Learning | Kiran Vajapey | 18m |
Uses Google Street View images, cleans and crowdsources labels via Figure Eight to produce 3,000 annotations, trains a sliding‑window SVM baseline, then… | ||
| Sarcasm Detection : Achilles Heel of sentiment analysis | Anuj Gupta | 46m |
Sentiment analysis has been for long poster boy problem of NLP and has attracted a lot of research. However, despite so much work in this sub area, most… | ||
| Recognizing Human features using Deep Networks | Akshay Bahadur | 21m |
This demo would be regarding some of the work that I have already done since starting my journey in Machine Learning. So, there are a lot of MOOCs out there… | ||
| Reinforcement Learning: Demystifying the hype | Samiran Roy, Om Deshmukh | 49m |
In 2014, Google accquired DeepMind, a small, london-based AI startup for $500 million. DeepMind was conducting research on AI that would learn to play computer… | ||
| Evolution to Systems Thinking from Model Thinking | Goda Ramkumar | 21m |
The talk provides a peek into different data science algorithms that come together to power a business like Ola. Area of focus would be on how different models… | ||
| The Artificial Intelligence Ecosystem driven by Data Science Community | Joy Mustafi | 45m |
Cognitive computing makes a new class of problems computable. To respond to the fluid nature of users understanding of their problems, the cognitive computing… | ||
| Computer Vision at the Edge with OpenVINO | Krishnakumar Shetti | 20m |
OpenVINO converts trained Caffe/TensorFlow/MXNet models to an intermediate IR (XML + .bin) with a model optimizer, then runs inference via a plugin-based… | ||
| Relationships Matter: Mining relationships using Deep Learning | Atul Singh | 21m |
The desire to reduce the cognitive load on human agents for processing swathes of data in natural languages is driving the adoption of machine learning based… | ||
| Applications of Generative Modeling | Vivek Singhal | 28m |
Generative Models are important techniques used in computer vision. Unlike other neural networks that are used for predictions from images, generative models… | ||
| Introduction to reinforcement learning using Python & OpenAI Gym | Saurabh Deshpande | 01h 21m |
Reinforcement Learning algorithms becoming more and more sophisticated every day which is evident from the recent win of AlphaGo and AlphaGo Zero… | ||
| DevOps for DS: Experiences from building a data science platform | Anand Chitipothu | 48m |
Productionizing data science applications is non trivial. Non optimal practices, the people-heavy way of the traditional approaches, the developers love for… | ||
| Explainable Artificial Intelligence (XAI): Why, When, and How? | Mridul Mishra | 48m |
Machine learning models are rapidly conquering uncharted grounds with new solutions by proving themselves to be better than the existing manual or software… | ||
| The Impact of Behavioral Biases to Real Data Science Projects | Rohit M. Lotlikar | 44m |
Data science projects, unlike their software counterparts tend to be uncertain and rarely fit into standardized approach. Each organization has it’s unique… | ||
| Connected Vehicle is far more than just the car | Savita Angadi | 46m |
For many IoT use cases there is a real challenge in streaming large amounts of data in real time, and the connected vehicle is no exception. Cars and trucks… | ||
| Using Open Data to Predict Market Movements | Asha Saini | 21m |
Claims a measurable correlation between media/article volume and vendor shifts in Gartner Magic Quadrants, demonstrated with NetApp and Hitachi Data Systems… | ||
| Building Case for Standardized Data Pipeline for Organizational Data | Gunjan Juyal | 20m |
Organizations of all size and domains today face a data explosion problem, driven by a proliferation of data management tools and techniques. A very common… | ||
| Building a Feature Platform to Scale Machine Learning | Will Pienaar | 45m |
Go‑Jek builds a production feature platform that makes feature code single-source and replayable: feature transforms run on Apache Beam/Dataflow, training sets… | ||
| Network Anomaly Detection and Root Cause Analysis | Veena Mendiratta | 46m |
Uses 4G per‑call measurement (PCMD) logs aggregated into 10‑second windows (≈700k records/min from one MME), one‑hot categorical frequencies and medians for… | ||
| Probabilistic Graphical Models, HMMs using PGMPY | Harish Kashyap K, Ria Aggarwal | 01h 23m |
Covers building and querying generative probabilistic models with the open source pgmpy library, showing how to enter CPDs, run variable elimination queries… | ||
| Prototypes to products: Build & deploy at-scale DS driven products | Om Deshmukh | 51m |
Have you ever wondered what it takes to demonstrate the efficacy of a data-driven approach to solve a particular problem and then build it into a full-fledged… | ||
| Hybrid Recommendation Systems using Probabilistic Graphical Models | Tuhin Kanti Sharma | 30m |
Hybrid system builds a Bayesian-style graph that combines LDA topics with genres and video IDs to capture both content and co‑occurrence signals, training a… | ||
| Sentiment Analysis with Deep Learning, ML or Lexicon Based | Kathrin Melcher | 01h 28m |
Hands‑on build of a sentiment app using KNIME Analytics Platform that reads files or crawled web and extracts text from PDFs and HTML, creates a document… | ||
| Art of Effective Visualization of Multi-dimensional Data | Dipanjan Sarkar | 51m |
Hands-on recipes for visualizing 1–6D structured data using Python (matplotlib, pandas, seaborn, plotnine) favor faceting over 3D and combine color, size… | ||
| Deep Learning with Apache Spark | Favio Vázquez | 54m |
Shows how to run Databricks’ Deep Learning Pipelines (spark-deep-learning) on Spark 2.3+, read images with the new image reader, and do transfer learning with… | ||
| Topological space creation and Clustering at BigData scale | Kuldeep Jiwani | 51m |
Every data has an inherent natural geometry associated with it. We are generally influenced by how the world visually appears to us and apply the same flat… | ||
| How to build propensity model where churn is single digit | Ujjyaini Mitra | 50m |
A telecom with single-digit churn (around 3%) builds microsegments by Cartesian-producting three CDR-derived features: daytime work/home cell clusters… | ||
| Embedding Artificial Intelligence in Spreadsheet | Santosh Vutukuri | 29m |
In today's world all of us are growing our data science capabilities. There are many such organizations who think they are comfortable in spreadsheets (e.g… | ||
| Let the Machine THINK for You | Srijak Bhaumik | 21m |
Every organization is now focused on the business or customer data and trying hard to get actionable insights out of it. Most of them are either hiring data… | ||
| Deep Learning in the Browser | Bargava Subramanian, Amit Kapoor | 48m |
Live demos show models running client-side: an explorable loan-default visualization that exposes thresholds and business impact, a real-time sentiment… | ||
| Architectural Decisions for Interactive Viz | Amit Kapoor, Bargava Subramanian | 46m |
Outlines concrete architecture choices for interactive visualization at scale: for millions-to-billions of points use bin-summarise-smooth (Datashader) or… | ||
| Operating at scale with Elastic Search in production | Subramaniajeeva Kandasamy | 24m |
Having problems in your application taking hours of effort to debug because of needle in a haystack of errors? Or unable to find anomalies quickly before it… | ||
| How DeepRRP Works | Tarry Singh | 01h 36m |
Company deepkapha.ai explains a neuroscience-led research stack, a new activation family called ARiA (Adaptive Richards-curve weighted activation) derived from… | ||
| Bring in the Lawyers: Explainable AI Driven Decision-making | Vikas Agrawal | 43m |
Daniel Dennett (Tufts University) says “If it can’t do better than us at explaining what it’s doing, then don’t trust it.” Will I believe the machine's… | ||
| Welcome address and opening talk | Sheamus McGovern, Naresh Jain | 31m |
Conference opens with concrete audience and program numbers: 544 attendees from 274 companies, 65 speakers from 9 countries, and 110 proposals, 67 accepted… | ||
| nothing matches | ||