The 7 Steps of Machine Learning (AI Adventures)

50 thoughts on “The 7 Steps of Machine Learning (AI Adventures)”

  1. I've put a lot of effort into this. Take a look.

    Hi everyone, i'm a a Software Engineering student graduating in Italy and I love Machine Learning.

    How many times, trying to approach Machine Learning, you felt baffled, disoriented and without a real "path" to follow, to ensure yourself a deep knowledge and the ability to apply it?

    This field is crazily exciting, but being rapid and "new" at the same time, it can be confusing to understand what each things means, and have a coherent naming of the things across resources and tutorials.

    I recently landed my first internship for a Data Science position in a shiny ML startup. My boss asked me if it was possible to create a study path for me and newcomers, and i've put a lot of efforts to share my 4-5 years of walking around the internet and collecting sources, projects, awesome tools, tutorial, links, best practices in the ML field, and organizing them in a awesome and useable way.

    You will get your hands dirty and learn in parallel theory and practice (which is the only efffective way to learn).

    The frameworks i've chosen is Scikit-Learn for generic ML tasks and TensorFlow for Deep Learning, and I'll update the document weekly.

    No prior knowledge is required, just time and will.

    Feel free to improve it and share with everyone.

    Inb4: sorry for my english, it's not my native language 🙂

    https://github.com/clone95/Machine-Learning-Study-Path/blob/master/README.md

  2. A hydrometer will not tell you the alcohol content of a given liquid unless you also have the original gravity.

  3. tuning hyperparameters is a science when you automatically tune them using a script and performance metrics..

  4. Y = m * x + b came out of nowhere without context, need to get that explanation clear and contextualised with everything else which is clear

    Also that is a time series graph which isn’t explained, formula for straight line is y = m * x + b

  5. Why google is using music from apple of the 90's, they should hire someon like arca or sophie or that japanese guy who made the music for the revenant

  6. so lets say i make AI to tell who is playing what song Sting or the beatles lets say i play steely dan

    can i make it say ? (i dont know )
    or say (this is not Sting or the beatles)

  7. As a new technology, it’s clear the full capabilities of AI have yet to emerge. It’s also clear that, as they improve and become more accessible, it will have many applications for online education. https://www.createonlineacademy.com/

  8. based on principles of "Machine Learning" analysis, as well as ca.5 experience in statistics/econometrics, advanced modeling for high value decision-making and general pattern, I would be much sought employee earning at least 50k (here in EU, local currency). For last 4 years I am unemployed. Am I the unfortunate proof that ML is making mistakes ? so how it is gonna be ?

  9. I know next to nothing about machine learning, 3:00 however, I can't believe that if you collected more data on beer than wine your model would guess (wrongly) too often something is a beer. That implies it is better to have less data, as long as it is evenly matched between variables. This makes no logical sense. It should always be best to have more data than less. Can someone please confirm or help?

  10. Can you please teach an AI bot to tell where the summoner spawns in diablo 2? (No one has ever found out and apparently its 100% random but I have always felt like there HAS to be some logic to it!

  11. Guo you need to whoa on machine learning. AI will be the end of us. Louise Cypher says end of humanity by 2025/2040 and that AI takes over.

  12. If you are stating an order of how to watch the videos, then why do the videos loop from first to second, and back to first again?

  13. Check out kaggle kernels where I implemented real world machine learning projects.This will help you to observe the pattern involved in data science

    Project 1.

    California Housing – ( optimised modelling )

    This project deals with advance concepts of machine learning along with 90% more important that machine learning .ie data pre-processing.

    Project 2.

    Indian Startup Funding (In-depth analysis)

    This paper shows the insights of funding done by startups and how growth changed with several factors. The aim of paper is to get a descriptive overview and a relationship pattern of funding and growth of newly launched startups. Another important point to understand how funding changes with time is an important aspect.

    Project 3.

    MNIST (tensorflow ) 99% accuracy

    MNIST ("Modified National Institute of Standards and Technology") is the de facto “hello world” dataset of computer vision. Since its release in 1999, this classic dataset of handwritten images has served as the basis for benchmarking classification algorithms. As new machine learning techniques emerge, MNIST remains a reliable resource for researchers and learners alike.

    Project4 –

    Titanic M.L | Kaggle

    Dataset is regarding The ship (titanic) whick sank in 1912 by a floating glacier in atlantic.

    The aim to predict passenger who survived in the chaos.
    Features such as ticket,age,class can be used to predict results. Dataset is not clean has high missing/nan values
    Project 5

    Internet Advertisements Detector(optimised) | Kaggle

    Advertisements Images detection -U.C.I

    This dataset represents a set of possible advertisements on Internet pages.

    The features encode :-

    the geometry of the image (if available)
    phrases occuring in the URL
    the image's URL and alt text
    the anchor text,
    words occuring near the anchor textThe task is to predict whether an image is an advertisement ("ad") or not ("nonad")
    Project 6.

    Credit Card Ensemble Detectors

    The datasets contains transactions made by credit cards in September 2013 by european cardholders.
    This dataset presents transactions that occurred in two days, where we have 492 frauds out of 284,807 transactions. 0.172% transations were fraud
    The Aim is to detect fraud transactions

    link- https://www.kaggle.com/manisood001
    checkout all the kernels

  14. I like the content of the video. But I would say for me personally it would be better to show only diagrams, because the movement of the person was kind of distraction. I would be happy to know who is demostrating though but not throughout the video…

  15. Explanation of most important training part is not clear. And I don't like the picture you used. Terrible example.

  16. Wow input model and output . If output is acceptable then fine if not feedback to obtain right answer. Explained nicely…great to visit this channel .

  17. This is the best video that ever explain to me how and why there are training and testing datasets. Great Great Job!!!

  18. Great pace but the lack of accuracy may lead a newbie to big confusion. 1-The shape of b is not correct, 2-you illustrate linear regression while it is a logistic regression case and 3-we choose model parameters using validation data set before the model evaluation using test data set not after.

Leave a Reply

Your email address will not be published. Required fields are marked *