Preparing and architecting for machine learning (handouts)

Page 1

Preparing and Architecting for Machine Learning

https://www.netcomlearning.com/webinars/?advid=1315


Agenda • Introduction to Machine Learning • Integrating Machine Learning with Big Data • Understanding Machine Learning and Robotics • Programming a Machine • Top AI technologies and how to identify the best fit

https://www.netcomlearning.com/webinars/?advid=1315


Understanding the difference between Analytics, Machine Learning, and Artificial Intelligence

https://www.netcomlearning.com/webinars/?advid=1315


AI

https://www.netcomlearning.com/webinars/?advid=1315


TL;DR (The very short summary)

https://www.netcomlearning.com/webinars/?advid=1315


Classical ML: Tasks

https://www.netcomlearning.com/webinars/?advid=1315


https://www.netcomlearning.com/webinars/?advid=1315


Classical ML: Features

https://www.netcomlearning.com/webinars/?advid=1315


Types of Machine Learning • Supervised learning, where observations contain input/output pairs (aka labeled data): These sample pairs are used to "train" the machine learning system to recognize certain rules for correlating inputs to outputs. Examples include types of ML that are trained to recognize a shape based on a series of shapes in pictures. • Unsupervised learning, where those labels are omitted: In this form of ML, rather than being "trained" with sample data, the machine learning system finds structures and patterns in the data on its own. Examples include types of ML that recognize patterns in attributes from input data that can be used to make a prediction or classify an object. • Reinforcement learning, where evaluations are given about how good or bad a certain situation is: Examples include types of ML that enable computers to learn to play games or drive vehicles https://www.netcomlearning.com/webinars/?advid=1315


Machine Learning vs. Programming

https://www.netcomlearning.com/webinars/?advid=1315


Deep Learning

https://www.netcomlearning.com/webinars/?advid=1315


https://www.netcomlearning.com/webinars/?advid=1315


https://www.netcomlearning.com/webinars/?advid=1315


https://www.netcomlearning.com/webinars/?advid=1315


Machine Learning Programming

https://www.netcomlearning.com/webinars/?advid=1315


Features/Attributes of Data

https://www.netcomlearning.com/webinars/?advid=1315


https://www.netcomlearning.com/webinars/?advid=1315


https://www.netcomlearning.com/webinars/?advid=1315


Integrating Machine Learning with Big Data

https://www.netcomlearning.com/webinars/?advid=1315


Data Ingestion and ELT

Distributed Storage, Compute, and Reporting

https://www.netcomlearning.com/webinars/?advid=1315


Machine Learning Architecture

https://www.netcomlearning.com/webinars/?advid=1315


https://www.netcomlearning.com/webinars/?advid=1315


Understanding Machine Learning and Robotics 1 – Computer Vision Robot vision is very closely linked to machine vision, which can be given credit for the emergence of robot guidance and automatic inspection systems. The slight difference between the two may be in kinematics as applied to robot vision, which encompasses reference frame calibration and a robot’s ability to physically affect its environment. https://www.youtube.com/watch?v=eQLcDmfmGB0

2 – Imitation Learning Imitation learning is closely related to observational learning, a behavior exhibited by infants and toddlers. Imitation learning is also an umbrella category for reinforcement learning, or the challenge of getting an agent to act in the world so as to maximize its rewards. Bayesian or probabilistic models are a common feature of this machine learning approach. https://player.vimeo.com/video/92149421

https://www.netcomlearning.com/webinars/?advid=1315


3 – Self-Supervised Learning Self-supervised learning approaches enable robots to generate their own training examples in order to improve performance; this includes using a priori training and data captured close range to interpret “long-range ambiguous sensor data.” It’s been incorporated into robots and optical devices that can detect and reject objects (dust and snow, for example); identify vegetables and obstacles in rough terrain; and in 3D-scene analysis and modeling vehicle dynamics (https://youtu.be/cLUCYPWi9Xo)

4 – Assistive and Medical Technologies An assistive robot (according to Stanford’s David L. Jaffe) is a device that can sense, process sensory information, and perform actions that benefit people with disabilities and seniors (though smart assistive technologies also exist for the general population, such as driver assistance tools). Movement therapy robots provide a diagnostic or therapeutic benefit. 5 – Multi-Agent Learning Coordination and negotiation are key components of multi-agent learning, which involves machine learning-based robots (or agents – this technique has been widely applied to games) that are able to adapt to a shifting landscape of other robots/agents and find “equilibrium strategies.” Examples of multi-agent learning approaches include noregret learning tools, which involve weighted algorithms that “boost” learning outcomes in multi-agent planning, and learning in market-based, distributed control systems.

https://www.netcomlearning.com/webinars/?advid=1315


Programming a Machine

https://www.netcomlearning.com/webinars/?advid=1315


https://www.netcomlearning.com/webinars/?advid=1315


https://www.netcomlearning.com/webinars/?advid=1315


https://www.netcomlearning.com/webinars/?advid=1315


https://www.netcomlearning.com/webinars/?advid=1315


https://www.netcomlearning.com/webinars/?advid=1315


https://www.netcomlearning.com/webinars/?advid=1315


https://www.netcomlearning.com/webinars/?advid=1315


https://www.netcomlearning.com/webinars/?advid=1315


https://www.netcomlearning.com/webinars/?advid=1315


Top AI technologies and how to identify the best fit

https://www.netcomlearning.com/webinars/?advid=1315


https://www.netcomlearning.com/webinars/?advid=1315


H2O.ai H2O.ai, which is based in Mountain View, California, U.S., offers an open-source machine-learning platform. For this Magic Quadrant, we evaluated H2O Flow, its core component; H2O Steam; H2O Sparkling Water, for Spark integration; and H2O Deep Water, which provides deep-learning capabilities. H2O.ai has progressed from Visionary in the prior Magic Quadrant to Leader. It continues to progress through significant commercial expansion, and has strengthened its position as a thought leader and an innovator. Databricks Databricks is based in San Francisco, California, U.S. It offers the Apache Spark-based Databricks Unified Analytics Platform in the cloud. In addition to Spark, it provides proprietary features for security, reliability, operationalization, performance and real-time enablement on Amazon Web Services (AWS). Databricks announced a Microsoft Azure Databricks platform for preview in November 2017, which is not considered in this Magic Quadrant because it was not generally available at the time of evaluation.

https://www.netcomlearning.com/webinars/?advid=1315


Recorded Webinar Video To watch the recorded webinar video for live demos, please access the link: https://bit.ly/2sDJcUM

https://www.netcomlearning.com/webinars/?advid=1315


About NetCom Learning

https://www.netcomlearning.com/webinars/?advid=1315


Recommended Courses » 20774: Perform Cloud Data Science with Azure Machine Learning - Class scheduled on June 25 » OD20774: Perform Cloud Data Science with Azure Machine Learning MOD » 20773: Analyzing Big Data with Microsoft R - Class scheduled on June 25 » OD20773: Analyzing Big Data with Microsoft R MOD » Practical Data Science with Python - Class scheduled on June 25

» Data Science and Big Data Analytics » GL660 - Hadoop For Systems Administrators

https://www.netcomlearning.com/webinars/?advid=1315


The Applications of SDN in Cisco (Part 2) ITIL: 3 Reasons to Align DevOps with IT Service Management (ITSM) How to Transition from AutoCAD to Revit BIM - What You Must Know Changing Role of IT Leaders in the Digital Age Let the Battle Begin: SaaS, PaaS and IaaS The Five Phases of Ethical Hacking Windows Server 2016: Advanced Networking Features Microsoft Excel 301: Working with tables and Pivot Charts https://www.netcomlearning.com/webinars/?advid=1315


https://www.netcomlearning.com/webinars/?advid=1315


https://www.netcomlearning.com/webinars/?advid=1315


THANK YOU !!!

https://www.netcomlearning.com/webinars/?advid=1315


Turn static files into dynamic content formats.

Create a flipbook
Issuu converts static files into: digital portfolios, online yearbooks, online catalogs, digital photo albums and more. Sign up and create your flipbook.