In the last decade, deep neural networks have created a major paradigm shift in speech recognition. This has resulted in dramatic and previously unseen reductions in word error rate across a range of tasks. These improvements have fueled products such as voice search and voice assistants like Amazon Alexa and Google Home.

The main components of a speech recognition system are the acoustic model, lexicon, and language model. In recent years, the acoustic model has evolved from using Gaussian mixture models to deep neural networks, resulting in significant reductions in word error rate. Recurrent neural network language models have also given improvements over the traditional statistical n-gram language models. More recently sequence to sequence recurrent neural network models have subsumed the acoustic model, lexicon, and language model into one system, resulting in a far simpler model that gives comparable accuracy to the traditional systems. This talk will outline this evolution of speech recognition technology, and close with some key challenges and interesting new areas to apply this technology.

Through the conference, we would have heard different speaker's perspective and experience with Data Science and AI. In this closing panel, we want to step back and look at any unanswered questions that the audience would have.

This talk will help you understand the vision behind ODSC Conference and how it has grown over the years.

Applying analytics to determine an optimal answer to business decision problems is relatively easy when the future can be predicted accurately. When the business environment is very complex and the future cannot be predicted, the business problem can become intractable using traditional modeling and problem-solving techniques. How do we solve such complex and intractable business problems to find globally optimal answers in highly uncertain business environments? The talk will discuss modeling and solution techniques that allow us to find optimal solutions in highly uncertain business environments without ignoring or underestimating uncertainty for revenue management and dynamic price optimization problems that arise in the airline and hospitality industry.

While architecting a data-based solution, one needs to approach the problem differently depending on the specific strategy being adopted. In traditional machine learning, the focus is mostly on feature engineering. In DL, the emphasis is shifting to tagging larger volumes of data with less focus on feature development. Similarly, synthetic data is a lot more useful in DL than ML. So, the data strategies can be significantly different. Both approaches require very similar approaches to the analysis of errors. But, in most development processes, those approaches are not followed leading to substantial delay in production times. Hyper parameter tuning for performance improvement requires different strategies between ML and DL solutions due to the longer training times of DL systems. Transfer learning is a very important aspect to evaluate in building any state of the art system whether ML or DL. The last but not the least is understanding the biases that the system is learning. Deeply non-linear models require special attention in this aspect as they can learn highly undesirable features.

In our presentation, we will focus on all the above aspects with suitable examples and provide a framework for practitioners for building ML/DL applications.

Cleaning, Preparing , Transforming and Exploring Data is the most time-consuming and least enjoyable data science task, but one of the most important ones. With Optimus we’ve solve this problem for small or huge datasets, also improving a whole workflow for data science, making it easier for everyone. You will learn how the combination of Apache Spark and Optimus with the Python ecosystem can form a whole framework for Agile Data Science allowing people and companies to go further, and beyond their common sense and intuition to solve complex business problems.

Accurate demand forecasts can help on-line retail organizations better plan their supply-chain processes. The chal- lenge, however, is the large number of associative factors that result in large, non-stationary shifts in demand, which traditional time series and regression approaches fail to model. In this paper, we propose a Neural Network architecture called AR-MDN, that simultaneously models associative fac- tors, time-series trends and the variance in the demand. We first identify several causal features and use a combination of feature embeddings, MLP and LSTM to represent them. We then model the output density as a learned mixture of Gaussian distributions. The AR-MDN can be trained end-to-end without the need for additional supervision. We experiment on a dataset of an year’s worth of data over tens-of-thousands of products from Flipkart. The proposed architecture yields a significant improvement in forecasting accuracy when compared with existing alternatives.

The browser is the most common end-point consumption of deep learning models. It is also the most ubiquitous platform for programming available. The maturity of the client-side JavaScript ecosystem across the deep learning process—Data Frame support (Arrow), WebGL-accelerated learning frameworks (deeplearn.js), declarative interactive visualization (Vega-Lite), etc.—have made it easy to start playing with deep learning in the browser.

Amit Kapoor and Bargava Subramanian lead three live demos of deep learning (DL) for explanations, inference, and training done in the browser, using the emerging client-side JavaScript libraries for DL with three different types of data: tabular, text, and image. They also explain how the ecosystem of tools for DL in the browser might emerge and evolve.

Demonstrations include:

1. Explorable explanations: Explaining the DL model and allowing the users to build intuition on the model helps generate insight. The explorable explanation for a loan default DL model allows the user to explore the feature space and threshold boundaries using interactive visualizations to drive decision making.
2. Model inference: Inference is the most common use case. The browser allows you to bring your DL model to the data and also allows you test how the model works when executed on the edge. The demonstrated comments sentiment application can identify and warn users about the toxicity of your comments as you type in a text box.
3. Rapid prototyping: Training DL models is now possible in the browser itself, if done smartly. The rapid prototyping image classification example allows the user to play with transfer learning to build a model specific for a user-generated image input.

The demos leverage the following libraries in JavaScript:

• Arrow for data loading and type inference
• Facets for exploratory data analysis
• ml.js for traditional machine learning model training and inference
• deeplearn.js for deep learning model training and inference
• Vega and Vega-Lite for interactive dashboards

The working demos will be available on the web and as open source code on GitHub.

Visualization is an integral part of the data science process and includes exploratory data analysis to understand the shape of the data, model visualization to unbox the model algorithm, and dashboard visualization to communicate the insight. This task of visualization is increasingly shifting from a static and narrative setup to an interactive and reactive setup, which presents a new set of challenges for those designing interactive visualization applications.

Creating visualizations for data science requires an interactive setup that works at scale. Bargava Subramanian and Amit Kapoor explore the key architectural design considerations for such a system and discuss the four key trade-offs in this design space: rendering for data scale, computation for interaction speed, adapting to data complexity, and being responsive to data velocity.

• Rendering for data scale: Envisioning how the visualization can be displayed when data size is small is not hard. But how do you render interactive visualization when you have millions or billions of data points? Technologies and techniques include bin-summarise-smooth (e.g., Datashader and bigvis) and WebGL-based rendering (e.g., deck.gl).
• Computation for interaction speed: Making the visualization reactive requires the user to have the ability to interact, drill down, brush, and link multiple visual views to gain insight. But how do you reduce the latency of the query at the interaction layer so that the user can interact with the visualization? Technologies and techniques include aggregation and in-memory cubes (e.g., hashcubes, InMEMS, and nanocubes), approximate query processing and sampling (e.g., VerdictDB), and GPU-based databases (e.g., MapD).
• Adapting to data complexity: Choosing a good visualization design for a singular dataset is possible after a few experiments and iterations, but how do you ensure that the visualization will adapt to the variety, volume, and edge cases in the real data? Technologies and techniques include responsive visualization to space and data, handling high cardinality (e.g., Facet Dive), and multidimensional reduction (e.g., Embedding Projector).
• Being responsive to data velocity: Designing for periodic query-based visualization refreshes is one thing, but streaming data adds a whole new level of challenge to interactive visualization. So how do you work decide between the trade-offs of real-time and near real-time data and their impact on refreshing visualization? Technologies and techniques include optimizing for near real-time visual refreshes and handling event- and time-based streams.

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 process of investigating social structures through the use of network and graph theories. It characterizes networked structures in terms of nodes (individual actors, people, or things within the network) and the ties or edges (relationships or interactions) that connect them. This is emerging as an important tool to understand customer behavior and influencing his behavior. The talk will focus on the mathematics behind SNA and how SNA can help make marketing decisions for telecom operators.

SNA use case will use telecom consumer data to establish networks based on their calling behavior like frequency, duration of calls, types of connections and thus establish major communities and influencers. By identifying key influencers and active communities marketing campaigns can be made more effective/viral. It helps in improving the adoption rate by targeting influencers with a large degree of followers. It will also touch upon how SNA helps retention rate and spread the impact of marketing campaigns. The tools used for use case is SAS SNA and Node XL for demonstration purpose. It will show how SNA helps in lifting the impact of campaigns.

This use case will illustrate a project focused on building a SNA model using a combination of demographic/firmographic variables for companies variables and Call frequency details. The dimensions like the company you work with, the place you stay, your professional experience and position, Industry Type etc. helps add a lot more value to the social network graph. With the right combination of the dimensions and problem at hand, in our case, it was more of marketing analytics we can identify the right influencers within a network. The more dimensions we add, the network gets stronger and more effective for running campaigns.

Looking forward to discussing the outcomes of this project with the audience and fellow speakers

Recently, we have heard success stories on how deep learning technologies are revolutionizing many industries. Deep Learning has proven huge success in some of the problems in unstructured data domains like image recognition; speech recognitions and natural language processing. However, there are limited gain has been shown in traditional structured data domains like BFSI. This talk would cover American Express’ exciting journey to explore deep learning technique to generate next set of data innovations by deriving intelligence from the data within its global, integrated network. Learn how using credit card spend data has helped improve credit and fraud decisions elevate the payment experience of millions of Card Members across the globe.

Cognitive computing makes a new class of problems computable. To respond to the fluid nature of users understanding of their problems, the cognitive computing system offers a synthesis not just of information sources but of influences, contexts, and insights. These systems differ from current computing applications in that they move beyond tabulating and calculating based on pre-configured rules and programs. They can infer and even reason based on broad objectives. In this sense, cognitive computing is a new type of computing with the goal of more accurate models of how the human brain or mind senses, reasons, and responds to stimulus. It is a field of study which studies how to create computers and computer software that are capable of intelligent behavior. This field is interdisciplinary, in which a number of sciences and professions converge, including computer science, electronics, mathematics, statistics, psychology, linguistics, philosophy, neuroscience and biology. Project Features are Adaptive: They MUST learn as information changes, and as goals and requirements evolve. They MUST resolve ambiguity and tolerate unpredictability. They MUST be engineered to feed on dynamic data in real time; Interactive: They MUST interact easily with users so that those users can define their needs comfortably. They MUST interact with other processors, devices, services, as well as with people; Iterative and Stateful: They MUST aid in defining a problem by asking questions or finding additional source input if a problem statement is ambiguous or incomplete. They MUST remember previous interactions in a process and return information that is suitable for the specific application at that point in time; Contextual: They MUST understand, identify, and extract contextual elements such as meaning, syntax, time, location, appropriate domain, regulation, user profile, process, task and goal. They may draw on multiple sources of information, including both structured and unstructured digital information, as well as sensory inputs (visual, gestural, auditory, or sensor-provided). {A set of cognitive systems is implemented and demonstrated as the project J+O=Y}

Data science projects, unlike their software counterparts tend to be uncertain and rarely fit into standardized approach. Each organization has it’s unique processes, tools, culture, data and in-efficiencies and a templatized approach, more common for software implementation projects rarely fits.

In a typical data science project, a data science team is attempting to build a decision support system that will either automate human decision making or assist a human in decision making. The dramatic rise in interest in data sciences means the typical data science project has a large proportion of relatively inexperienced members whose learnings draw heavily from academics, data science competitions and general IT/software projects.

These data scientists learn over time that the real world however is very different from the world of data science competitions. In the real-word problems are ill-defined, data may not exist to start with and it’s not just model accuracy, complexity and performance that matters but also the ease of infusing domain knowledge, interpretability/ability to provide explanations, the level of skill needed to build and maintain it, the stability and robustness of the learning, ease of integration with enterprise systems and ROI.

Human factors play a key role in the success of such projects. Managers making the transition from IT/software delivery to data science frequently do not allow for sufficient uncertainty in outcomes when planning projects. Senior leaders and sponsors, are under pressure to deliver outcomes but are unable to make a realistic assessment of payoffs and risks and set investment and expectations accordingly. This makes the journey and outcome sensitive to various behavioural biases of project stakeholders. Knowing what the typical behavioural biases and pitfalls makes it easier to identify those upfront and take corrective actions.

The speaker brings his nearly two decades of experience working at startups, in R&D and in consulting to lay forth these recurring behavioural biases and pitfalls.

Many of the biases covered are grounded in the speakers first-hand experience. The talk will provide examples of these biases and suggestions on how to identify and overcome or correct for them.

Are you or your customers running on Apache Hadoop and Spark clusters? Are you curious on how you can run Deep Learning for inference and training datasets on your existing Hadoop or Spark CPU clusters without having to migrate your data from one setup to another – experience how easy it is to run DL on your general purpose CPU. This workshop will help you - Get Started on your journey with Intel's Big Data Deep learning Library - BigDL.

Join AI experts at Intel for a deep-dive workshop to learn about computer vision and deep learning.

• Technical overview of BigDL architecture and learn:
  • How it fits in the Apache Spark stack
  • Key features
  • Resources, code samples, and tips
• Build with BigDL
  • Learn how to deploy BigDL on-premise or in the cloud to build end-to-end solutions.
  • Review case studies
  • Experience real-life demos

Generative Models are important techniques used in computer vision. Unlike other neural networks that are used for predictions from images, generative models can generate new images for specific objectives. This session will review several applications of generative modeling such as artistic style transfer, image generation and image translation using CNNs and GANs.

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 for ML and data science but the most important thing is to apply the concepts learned during the course to solve simple real-world use cases.

• One of the projects that I did included building state of the art Facial recognition system [VIDEO]. So for that, I referred to several research papers and the foundation was given to me in one of the courses itself, however, it took a lot of effort to connect the dots and that's the fun part.
• In another project, I made an Emoji Classifier for humans [VIDEO] based on your hand gestures. For that, I used deep learning CNN model to achieve great accuracy. I took reference from several online resources that made me realize that the data science community is very helpful and we must make efforts to contribute back.
• The other projects that I have done using machine learning:
  1. Handwritten digit recognition [VIDEO],
  2. Alphabet recognition [VIDEO],
  3. Apparel classification [VIDEO],
  4. Devnagiri recognition [VIDEO].

With each project, I have tried to apply one new feature or the other to make my model a bit more efficient. Hyperparameter tuning or just cleaning the data.

In this demonstration, I would just like to point out that knowledge never goes to waste. The small computer vision applications that I built in my college has helped me to gain deep learning computer vision task. It's always enlightening and empowering to learn new technologies.

I recently was part of a session on ‘Solving real world applications from Machine learning’ to Microsoft Advanced Analytics User Group of Belgium as well as broadcasted across the globe (Meetup Link) [Session Recording]

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 software solutions for extracting structured information from unstructured text for a variety of use case scenarios such as monitoring Internet sites for potential terror threat and analyzing documents from disparate sources to identify potentially illegal transactions. These aforementioned software solutions for extracting structured information from unstructured text rely on the ability to identify the entities and the relationship between the entities using Natural Language Processing that has benefitted immensely from the progress in deep learning.

The goal of this talk is to introduce relationship extraction a key plinth stone of natural language understanding, and its use for building knowledge graphs to represent structured information extracted from unstructured text. The talk demonstrates how deep learning lends itself well to the problem of relationship extraction and provides an elegant and simple solution.

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 recommendation enough to make a serious decision? What if need to explain my decision in court or to my shareholders or to individual customers? Is high precision and recall enough? We will see some examples where integrative AI models get better and better at providing actionable intelligence such that to ignore the advice could be considered irresponsible, reckless or discriminatory. Who would be to blame if the advice given by the AI system is found erroneous or disregarded? Then, the advice given by the AI system itself becomes confidential attorney-client privileged communication, and there are real debates around giving the privilege of plausible deniability to senior leadership of corporations.

Wouldn't it be better to provide an explanation for the recommendations, and let the humans decide whether the advice makes sense? Moreover, in some geographies like Europe (GPDR), and in industries like banking, credit cards and pharmaceuticals, the explanations for predictions (or decision rules derived from them) are required by regulatory agencies. Therefore, many of these industries limit their models to easily explainable white box algorithms like logistic regression or decision trees. What kind of explanations would it take for regulatory agencies to be willing to accept black-box algorithms such are various types of NNs for detecting fraud or money-laundering? How do we demonstrate to the end-user what the underlying relationships between the inputs and outputs are, for traditionally black-box systems? How could we influence decision-makers enough to place trust in predictions made by a model? We could begin by giving reasons, explanations, substantial insights into why a pump is about to fail in the next three days, or how a sales opportunity is likely to be a win or why an employee is leaving. Yet, if we don't make these relevant to your role, your work context, your interests, what is valuable to you and what might you lose if you make an incorrect decision, then we have not done our job as data scientists.

Explanations are the core of the evolving relationship between humans and intelligent machines - this fosters trust. We need to be just as cautious of AI explanations as we are of each other’s—no matter how clever a machine seems. This means as a community we need to find ways of reliably explaining black-box models. David Gunning (DARPA) says.“It’s the nature of these machine-learning systems that they produce a lot of false alarms, so an intelligence analyst really needs extra help to understand why a recommendation was made."

In this talk, we will examine what is required to explain predictions, the latest research in the area, our own findings showing how it is currently being accomplished in practice for multiple real-world use cases in the enterprise

In these two training sessions ( 4 hours each, 8 hours total), you will learn to use data visualization and analytics software Tableau Public (free to use) and turn your data into interactive dashboards. You will get hands on training on how to create stories with dashboards and share these dashboards with your audience. However, the first session will begin with a quick refresher of basics about design and information literacy and discussions about best practices for creating charts as well as decision making framework. Whether your goal is to explain an insight or let your audience explore data insights, Tableau's simple drag-and-drop user interface makes the task easy and enjoyable. You will learn what's new in Tableau and the session will cover the latest and most advanced features of data preparation.

In the follow up second session, you will learn to create Table Calculations, Level of Detail Calculations, Animations and understanding Clustering. You will learn to integrate R and Tableau and how to use R within Tableau. You will also learn mapping, using filters / parameters and other visual functionalities.