Go gaga over Machine Learning

Data science team at Dell EMC uses a methodology called DEPP that guides the collaboration with the business stakeholders through the following stages: Descriptive Analytics to clearly understand what happened and how the business is measuring success. Exploratory Analytics to understand the financial, business and operational drivers behind what happened. Predictive Analytics to transition the business stakeholder mindset to focus on predicting what is likely to happen. Prescriptive Analytics to identify actions or recommendations based upon the measures of business success and the Predictive Analytics. The DEPP Methodology is an agile and iterative process that continues to evolve in scope and complexity as the clients mature in their advanced analytics capabilities Read more at: Lessons in Becoming an Effective Data Scientist I was recently a guest lecturer at the University of California Berkeley Extension in San Francisco. On a lovely Saturday afternoon, the...

A Diagram Editor for JupyterLab - Jupyter Blog The new JupyterLab interface is much more than a replacement for the classic notebook. It aims to bring together all the pieces required for a complete scientific workflow. The extension-based architecture of JupyterLab comes with a number of components already enabled: a Jupyter notebook, a text editor, a file browser in the sidebar, a number of editors and viewers for various file formats, and much more.

I often wonder when I see people completing certificates on ML, are these more for showing the world that you know and understand ML or is it really a sense of achieving something! If it is the latter then why pay ? and why need a certificate at all? Let me elaborate on the resources that are free and can do a better job than most paid ML courses: Googles free website to choose videos, docs,tutorials, courses , sample code and Interactive demos -  https://ai.google/education/#?modal_active=none Have you read this? Triskelion one of the leaders on Kaggle explains how he went from a  beginner and finished up as a master with a top 10 finish -  https://mlwave.com/reflecting-back-on-one-year-of-kaggle-contests/  or  https://machinelearningmastery.com/master-kaggle-by-competing-consistently/ Kaggles Learning modules that are amazing  Machine Learning -  https://www.kaggle.com/learn/machine-learning R -  https://www.kaggle.co...

Here is an interesting illustration that might help you to choose your ML algorithm.  Source: scikit-learn.org

The best ML learning path that helped me: Each subject does not require a whole day to be able to understand it fully, and you can do multiple of these in a day. Each day I take one subject from the list below, read it cover to cover, take notes, do the exercises and write an implementation in Python or R. Table of Contents What is it? Why use it? How to use it Don't feel you aren't smart enough Machine learning overview Machine learning mastery Machine learning is fun Inky Machine Learning Machine Learning: An In-Depth Guide Stories and experiences Machine Learning Algorithms Beginner Books Practical Books Kaggle knowledge competitions Video Series MOOC Resources Becoming an Open Source Contributor Games Podcasts Communities Conferences Interview Questions Source:  https://github.com/ZuzooVn/machine-learning-for-software-engineers Here is my post on Kaggle: https://www.kaggle.com/getting-started/48594#post275859

Source:  https://www.kdnuggets.com/2018/01/mlaas-amazon-microsoft-azure-google-cloud-ai.html

Good to see there are smart people having a futuristic vision in this space, though 2030 sounds far! New Australian innovation roadmap calls for focus on AI, machine learning Data science and artificial intelligence (AI) represent a significant economic opportunity for the Australian economy, according to a new report released by Innovation and Science Australia (ISA). ISA was tasked by the federal government with developing a strategic plan for the Australian innovation, science and research system out to 2030.

What is a Kernel? Kernels contain both the code that is needed for analysis and the analysis itself! "Kaggle Kernels is a cloud computational environment that enables reproducible and collaborative analysis. Kernels supports scripts in R and Python, Jupyter Notebooks, and RMarkdown reports. Go to the Kernels tab to view all of the publicly shared code on this competition. For more on how to use Kernels to learn data science, visit the Tutorials tab . " There are two types of Kernels on Kaggle: Notebook Scripts Script or notebook depends on what you are trying to achieve, If you were me then start with a notebook and move to a Script!

I recently gave a talk on ML and that has inspired me to tread down the path and explore more. I can't call it a recent post but it is a recent post  from  Jason Brownlee   that I read which has given me better direction to add some seriousness to this field Some key takeaway on how to start mine/your ML journey: DO NOT go through ML tutorials , Get onto hands-on realtime problems  Get onto Kaggle Follow the likes of Triskelion  Reproduce what others have done, DO NOT reinvent the wheel What other tools ? Vowpal Wabbit Scikit-learn R or Weka or Python or DO NOT have a weapon of choice "Competing consistently is the key to getting good." New to Data Science? Get started with a tutorial on our most popular competition for beginners, Titanic: Machine Learning from Disaster . Machine learning is the hottest field in data science, and this track will get you started quickly.  https://www.kaggle.com/learn/machine-learning Practice a lot : ...

Okay, I have been asked by a lot of people and if you follow my blog you’re probably wondering why did I change the name of my blog right?  Well, if you are not living under a rock you've probably heard about "Machine Learning" and how it's changing everything we do. Therefore the new name "Go gaga over Testing   Machine Learning" , all the posts going ahead will be very much focused in this direction. There is another reason "I love Alan Turing" :) Machine learning applications have the potential to disrupt industries, take pioneers miles ahead of competitors, and even create new revenue channels. Because cloud-based analytics solutions have become affordable for startups, we already have hundreds of business success stories that have been written using the power of machine learning. I haven’t officially changed the URL, so you will still type in go-gaga-over-testing.blogspot.com to access my site, but the name of the blog, logo, ...

Perfect start to Monday! Quick read that syncs the idea of how AML would be used in shaping the future of software testing: Machine Learning or Automation: What's the Difference? There's a lot of buzz in the tech industry, especially with cutting-edge technologies like artificial intelligence and machine learning becoming more mainstream. While many professionals understand that these technologies will make their jobs easier, or even take over certain tasks, there's also a lot of confusion: machine learning, automation - what's the difference between the two?

Solving the most common problem predicting house prices in any suburb using supervised learning. What's amazing is we shall build a Machine Learning model using MLJAR MLJAR is a human-first platform for machine learning. It provides a service for prototyping, development and deploying pattern recognition algorithms. It makes algorithm search and tuning painless! The basics of ML can be read anywhere on github/google. What we need to know is regression/classification and when to use what.  First things first test data: https://github.com/AdyKalra/MachineLearningHousing/tree/master/house_prices#house-prices train sample - (data_train.csv file) for model learning  test samples (data_test.csv) for predictions Create a new project Select Regression as a task Add train and test data Note - When we add test dataset check the option: This dataset will be used only for predictions because we want to predict the sale price Specify columns that we use , ta...

John Bates the CEO of Testplant has exactly my views on what smart and intelligent test automation would be: Quick snippets: 1. Intelligent automation  - The only way to realistically test a digital app is through an intelligent automation engine accessing the application as a user would - taking control of a machine, actually using the app to exercise workflows and collecting intelligent analytics along the way. This involves technology to understand on-screen images and text, such as smart image search and dynamic neural networks (so called “deep learning”). 2. Intelligent test coverage generation and ‘bug-hunting’  - There are a potentially infinite number of paths through a complex app so which ones should we follow in our automation? We can use AI classification algorithms such as Bayesian networks, to select paths and 'bug hunt'. As these paths are explored, the bug-hunting AI algorithm continues to learn from correlations in data to refine the coverage...

Testim -  https://www.testim.io/ Testim is a new test automation tool that claims to use machine learning to speed the authoring, execution, and maintenance of automated tests. "A developer can author a test case in minutes and execute them on multiple web and mobile platforms. We learn from every execution, self-improving the stability of test cases, resulting in a test suite that doesn't break on every code change. We analyze hundreds of attributes in realtime to identify each element vs. static locators. Little effort, if any, is then required to maintain these test cases yet they are stable and trustworthy." Being a huge enthusiast about Machine Learning in the test automation space , I am super excited and hope this is the beginning of a new way of testing. The CEO  Oren Rubin and COO Shani Shoham  - "We use dynamic locators and learn with every execution. The outcome is super fast authoring and stable tests that learn, thus eliminating the need ...

Roland Meertens  an AI developer detected bats and ended up using Tensor flow : jupyter notebook Labeling sound data - librosa library Loading sound data with Python  Visualizing sounds with Librosa Machine learning model - TensorFlow Github - https://github.com/rmeertens/batdetection Detecting bats by recognising their sound with Tensorflow Last week I discovered that there are bats behind my appartment. I immediately grabbed my "bat detector": a device that converts the ultrasound signals bats use to echolocate from an inaudible frequency range to an audible one. The name "bat detector" thus is a lie: you can use it to detect bats, but it does not detect bats itself.

Sydney to test driverless shuttle AUSTRALIA: A two-year trial of a driverless shuttle is due to begin later this month at Sydney Olympic Park, the New South Wales government announced on August 2. Testing of a driverless shuttle supplied by Navya will shortly begin on an enclosed pre-programmed route at Newington Armory.

Applitools raises $8 million for its quality assurance computer vision Software testing company Applitools has raised $8 million for its technology that uses computer vision to recognize changes to websites or mobile apps like typos, missing icons, or other content. Developers using Applitools can catch mistakes or spot variations between version history or web browsers. Tricentis reveals first JIRA testing tool, enabling agile teams feedback Tricentis has released its first exploratory testing tool for Atlassian JIRA's testing industries, enabling agile teams to keep pace with accelerated release cycles and for faster feedback on quality matters. Focusing on quality, testing times and resources, the software testing company will help agile teams reliably deliver comprehensive feedback on applications under test, whilst providing a flexible pace with constant change.

If you haven't heard of these then you have been living under a rock: Everest Group FIT matrix for Robotic Process Automation (rpa) technology   UiPath named RPA Industry Leader; scores Best RPA Technology - Forrester. UiPath, known for unrivaled Citrix automation performance with its computer vision technology, has been recognized as an RPA industry leader in the "Forrester Wave ™ Robotic Process Automation, Q1 2017". The report compared 12 RPA vendors against criteria in the areas of: current offering; strategy and market presence.

Or you can view on youtube @ TConf.io 2016 Aditya Kalra Testing insights: in the fast paced technology world of apps https://tconf.io http://mst.qa SDETs are the new technical testers, reshaping industries and changing how testing can be achieved. Success in this space depends on how well and how fast you respond. Testing Insights will give you answers to what you will be looking for and where you can find in the ever changing world of app test automation.