Hi [[ session.user.profile.firstName ]]

Machine Learning

  • Date
  • Rating
  • Views
  • Image recognition with deep learning
    Image recognition with deep learning Layla Tadjpour, Data Science Consultant, Ph.D. in Electrical Engineering from University of Southern California. Recorded: Oct 11 2017 39 mins
    In this webinar, we will learn about image recognition with deep learning. After a brief overview of what deep learning is, and why it matters, we will learn how to classify dogs from cats. That is, how to train a model to recognize dog images from cat images.

    We use Keras, an easy to use python deep learning library that sits on top of Tensorflow, and “fine-tuning”, a very important skill for any deep learning practitioner, to train a model to classify the images.

    Once we trained our model to classify dogs from cats images with high accuracy, we dig into the details of the trained model and look at its building blocks, i.e., Convolutional Neural Networks (CNN), Fully Connected Block and activation functions to develop an understanding of how the deep learning model works.
  • Data scientists: Can't live with them, can't live without them.
    Data scientists: Can't live with them, can't live without them. Wyatt Benno, CEO, DataHero Recorded: Aug 24 2017 45 mins
    There has been a flood of publicity around big data, data processing, and the role of predictive analytics in businesses of the future.
    As business operators how do we get access to these valuable business insights, even when there is not a data analyst around to walk us through their results?

    - Should your software emulate a data scientist?
    - Learn about the power of data visualizations.
    - Learn about creating value from disperse data sets.
  • Hunting Criminals with Hybrid Analytics, Semi-supervised Learning, & Feedback
    Hunting Criminals with Hybrid Analytics, Semi-supervised Learning, & Feedback David Talby, CTO, Atigeo Recorded: Aug 23 2017 62 mins
    Fraud detection is a classic adversarial analytics challenge: As soon as an automated system successfully learns to stop one scheme, fraudsters move on to attack another way. Each scheme requires looking for different signals (i.e. features) to catch; is relatively rare (one in millions for finance or e-commerce); and may take months to investigate a single case (in healthcare or tax, for example) – making quality training data scarce.

    This talk will cover a code walk-through, the key lessons learned while building such real-world software systems over the past few years. We'll look for fraud signals in public email datasets, using IPython and popular open-source libraries (scikit-learn, statsmodel, nltk, etc.) for data science and Apache Spark as the compute engine for scalable parallel processing.

    David will iteratively build a machine-learned hybrid model – combining features from different data sources and algorithmic approaches, to catch diverse aspects of suspect behavior:

    - Natural language processing: finding keywords in relevant context within unstructured text
    - Statistical NLP: sentiment analysis via supervised machine learning
    - Time series analysis: understanding daily/weekly cycles and changes in habitual behavior
    - Graph analysis: finding actions outside the usual or expected network of people
    - Heuristic rules: finding suspect actions based on past schemes or external datasets
    - Topic modeling: highlighting use of keywords outside an expected context
    - Anomaly detection: Fully unsupervised ranking of unusual behavior

    Apache Spark is used to run these models at scale – in batch mode for model training and with Spark Streaming for production use. We’ll discuss the data model, computation, and feedback workflows, as well as some tools and libraries built on top of the open-source components to enable faster experimentation, optimization, and productization of the models.
  • Analytics Nightmares and How You Can Prevent Them
    Analytics Nightmares and How You Can Prevent Them Meta S. Brown, Author, Data Mining for Dummies and President, A4A Brown, Inc. Recorded: Aug 22 2017 49 mins
    Analytics risks can keep you up at night. What if…
    · We make a big investment and don’t break even?
    · Management doesn’t trust the results?
    · Analysts cross data privacy boundaries?

    What a dilemma! You see the perils, yet you want the rewards that analytics can bring. The appropriate process enables you to dramatically reduce risks and maximize returns on your data and analytics investment.

    In this presentation, you will learn:
    · What causes most analytics failures
    · How you can diminish risk and maximize returns through strong analytics process
    · Why you (yes, you!) have a pivotal opportunity to establish high standards for analytics process right now
  • Radiant, a powerful open source Shiny application for business analytics
    Radiant, a powerful open source Shiny application for business analytics Ali Marami Chief Data Scientist Recorded: Jul 11 2017 58 mins
    Radiant is a robust tool for business analytics and running sophisticated models without any need for code development. It leverages the functions and tools in R and at the same time provides a user-friendly interface. With Radiant, you can manipulate and visualize your data, run different models from simple OLS to decision trees (CART) and neural networks, and evaluate your results.

    The application is based on the Shiny package and can be run locally or on a server. Radiant was developed by Vicent Nijs. In this webinar, we review the tools available in Radiant and explain how easily you can use this tool without any setup or installation on your system.

    Radiant key features:

    • Explore: Quickly and easily summarize, visualize, and analyze your data
    • Run different models: OLS, GLM, Neural Networks, Naïve Bayes and CART.
    • Cross-platform: It runs in a browser on Windows, Mac, and Linux
    • Reproducible: Recreate results and share work with others as a state-file or an Rmarkdown report
    • Programming: Integrate Radiant's analysis functions with your own R-code
    • Context: Data and examples focus on business applications

    After this webinar you will learn:

    • Data manipulation and running different models
    • How to run advanced analytics in a browser on any device even in your tablet or iPad.

    Presenter bio:

    Ali has a Ph.D. in Finance from the University of Neuchatel in Switzerland and a BS in Electrical Engineering. He has extensive experience in financial modeling, quantitative modeling, and financial risk management in several US banks.
  • Binomial and Multinomial Logistic Regressions in R
    Binomial and Multinomial Logistic Regressions in R Ali Marami Chief Data Scientist Recorded: Jun 29 2017 49 mins
    Logistic regressions are the basic of machine learning. In this webinar, we discuss binomial and multinomial logistic regressions, how we implement them in R and test their performance. We will also review few examples of their usage in industry. In addition, you will learn how to use R-Brain advanced IDE when implementing the model.

    - Logistic regressions fundamentals and how to interpret estimates
    - Binomial and Multinomial logistic regressions
    - Implement logistic regressions in R
    - Performance measurement in logistic regressions
    - Generating and understanding ROC curve
    - Building confusion metrics and understanding its elements
    - Examples of model application in industry
    - Learn about new advanced IDE

    Presenter bio:

    Ali has a Ph.D. in Finance from the University of Neuchatel in Switzerland and a BS in Electrical Engineering. He has extensive experience in financial modeling, quantitative modeling, and financial risk management in several US banks.
  • Death to Traffic: How Smart Cities are Changing Transportation
    Death to Traffic: How Smart Cities are Changing Transportation Laura Schewel, CEO, StreetLight Data Recorded: Jun 23 2017 45 mins
    From automated vehicles to ride hailing apps, transportation as we know it is changing - and fast. But new technologies alone won't help communities build the efficient, equitable, and sustainable transportation networks communities want. In fact, these innovative technologies could do just the opposite, especially if they are not deployed wisely. Cities must collect the right data and enact the right policies to ensure they do not exacerbate problems like inequity and traffic, and to hold themselves accountable to the promise of new mobility technologies.

    In this webinar, you will find out why - and how - the smartest cities of tomorrow will be those that adopt data-driven transportation strategies today. Join for Laura Schewel's presentation to gain insights into:

    • Why the status quo for transportation data collection is no longer good enough
    • The types of Massive Mobile Data that are useful for transportation and urban planning
    • Algorithmic processing techniques that are critical for making this data useful
    • Case studies from California and Virginia that demonstrate why Massive Mobile Data drives more effective transportation planning
    • A forward-looking blueprint for using Massive Mobile Data to maximize the potential benefits of new transportation technologies - and minimize negative impacts

    Laura Schewel founded StreetLight Data, a mobility analytics provider, after spending more than a decade as an advanced transportation researcher and statistician at the Rocky Mountain Institute and FERC. She has particular expertise in transportation systems, sustainability and safety, and vehicle/system modeling and analysis.
  • How IoT Will Make Healthcare Healthy, Wealthy, & Wise
    How IoT Will Make Healthcare Healthy, Wealthy, & Wise Jarie Bolander, COO, Lab Sensor Solutions Recorded: Jun 23 2017 46 mins
    IoT is a technology that has the potential to make us healthy, wealthy, and wise especially in healthcare. Healthcare is just now adopting IoT to improve patient outcomes and decrease the cost of care.

    In this webinar, you’ll learn:

    - How to identify if an IoT solution will work for your use case.
    - What others in healthcare are using IoT for.
    - The challenges of IoT in healthcare
  • Panel: Smart Fog and Transaction Management for Cities and Maritime
    Panel: Smart Fog and Transaction Management for Cities and Maritime Moderator: Katalin Walcott (Intel) Panel: Jeff Fedders (OpenFog), Mark Dixon (IBM), Matthew Bailey (Powering IoT) Recorded: Jun 22 2017 61 mins
    Fog computing represents a tectonic shift for the future of transaction management, distributed supply chain and overall experience. It blurs the lines between the edge and the cloud and puts the focus on the systems which manage and balance the delivery of coherent, end-to-end sessions and associated transaction level agreements. As a result, this new technology is pervasive in several industries.

    Join this panel of experts as they discuss solutions with specific industry use cases from smart fog for Cities, Buildings, Ports, and Maritime.

    Moderator: Katalin Walcott, Work Group Chair Manageability at OpenFog Consortium & Principal Engineer - IoT/Fog Computing Orchestration Architecture at Intel

    - Jeff Fedders, President at OpenFog Consortium & Chief Strategist, IoTG Strategy and Technology Office at Intel
    - Mark Dixon, Senior Architect for Smarter Cities at IBM
    - Matthew Bailey, President, Powering IoT - Smart City advisor and strategist to governments, technology corporations, and economic development agencies
  • Toward Internet of Everything: Architectures, Standards, & Interoperability
    Toward Internet of Everything: Architectures, Standards, & Interoperability Ram D. Sriram, Chief of the Software and Systems Division, IT Lab at National Institute of Standards and Technology Recorded: Jun 21 2017 63 mins
    In this talk, Ram will provide a unified framework for Internet of Things, Cyber-Physical Systems, and Smart Networked Systems and Societies, and then discuss the role of ontologies for interoperability.

    The Internet, which has spanned several networks in a wide variety of domains, is having a significant impact on every aspect of our lives. These networks are currently being extended to have significant sensing capabilities, with the evolution of the Internet of Things (IoT). With additional control, we are entering the era of Cyber-physical Systems (CPS). In the near future, the networks will go beyond physically linked computers to include multimodal-information from biological, cognitive, semantic, and social networks.

    This paradigm shift will involve symbiotic networks of people (social networks), smart devices, and smartphones or mobile personal computing and communication devices that will form smart net-centric systems and societies (SNSS) or Internet of Everything. These devices – and the network -- will be constantly sensing, monitoring, interpreting, and controlling the environment.

    A key technical challenge for realizing SNSS/IoE is that the network consists of things (both devices & humans) which are heterogeneous, yet need to be interoperable. In other words, devices and people need to interoperate in a seamless manner. This requires the development of standard terminologies (or ontologies) which capture the meaning and relations of objects and events. Creating and testing such terminologies will aid in effective recognition and reaction in a network-centric situation awareness environment.

    Before joining the Software and Systems Division (his current position), Ram was the leader of the Design and Process group in the Manufacturing Systems Integration Division, Manufacturing Engineering Lab, where he conducted research on standards for interoperability of computer-aided design systems.

Embed in website or blog