Neural Networks from Scratch – P.5 Hidden Layer Activation Functions




[ad_1]

Neural Networks from Scratch book, access the draft now: https://nnfs.io

NNFSiX Github: https://github.com/Sentdex/NNfSiX

Playlist for this series: https://www.youtube.com/playlist?list=PLQVvvaa0QuDcjD5BAw2DxE6OF2tius3V3

Spiral data function: https://gist.github.com/Sentdex/454cb20ec5acf0e76ee8ab8448e6266c

Python 3 basics: https://pythonprogramming.net/introduction-learn-python-3-tutorials/
Intermediate Python (w/ OOP): https://pythonprogramming.net/introduction-intermediate-python-tutorial/

Mug link for fellow mug aficionados: https://amzn.to/3bvkZ6B

Channel membership: https://www.youtube.com/channel/UCfzlCWGWYyIQ0aLC5w48gBQ/join
Discord: https://discord.gg/sentdex
Support the content: https://pythonprogramming.net/support-donate/
Twitter: https://twitter.com/sentdex
Instagram: https://instagram.com/sentdex
Facebook: https://www.facebook.com/pythonprogramming.net/
Twitch: https://www.twitch.tv/sentdex

#nnfs #python #neuralnetworks

Source


[ad_2]

Comment List

  • sentdex
    December 15, 2020

    Grate work!

    how do i get nnfs 1.18.2 in sted of nnfs 1.19.2?
    i get lots of format errors and i think it comes with nnfs 1.19.2.

    errors like (return orig_dot(*[a.astype('float64') for a in args], **kwargs).astype('float32'))

  • sentdex
    December 15, 2020

    I love it and I want more

  • sentdex
    December 15, 2020

    World is waiting for P.6

  • sentdex
    December 15, 2020

    Hi Harrison, Any estimate when part 6 will be out? Thanks

  • sentdex
    December 15, 2020

    Amazing graphics and great explanation! Thank you so much for your effort in these videos!!!

  • sentdex
    December 15, 2020

    I am sorry to say this, but all of this so far could be nicely made into a single ~30 mins video. Why so much verbosity?

  • sentdex
    December 15, 2020

    when will part 6 be released?

  • sentdex
    December 15, 2020

    Where is your microphone?

  • sentdex
    December 15, 2020

    The paperback book just arrived! Wow it is huge in real life. Weighs like 2.6 kg (~5.75 pounds). WOW

  • sentdex
    December 15, 2020

    Bought your book, but still eagerly waiting for the next video. These are very well produced deep dives that are easy to understand.

  • sentdex
    December 15, 2020

    Where is the next video?

  • sentdex
    December 15, 2020

    Rip the series?

  • sentdex
    December 15, 2020

    part 6 man…please publish that

  • sentdex
    December 15, 2020

    part 6 ;___________;

  • sentdex
    December 15, 2020

    whether you turned off multilingual subtitles intentionally or accidentally. Otherwise the tutorial is great

  • sentdex
    December 15, 2020

    Hi! I'm using Jupiter Notebook and I can't import the nnfs package.
    It says "No module named 'nnfs'".
    How can I do it?

  • sentdex
    December 15, 2020

    waiting for part 6.

  • sentdex
    December 15, 2020

    Pls it so great project, don't stop!

  • sentdex
    December 15, 2020

    This may sound like a dumb question but I’m confused about your choice of values in your NNFS videos

    In your video on hidden layer activation the animation showed you (or rather David) adjusting the weights and biases to fit the form of that non-linear function. So is that how one would always choose what numeric values to use for weights and biases? Your videos often refer to the textbook for values so idk what values I would use for my own NN. I understand the concepts just not which numerical values to put into my own code.

  • sentdex
    December 15, 2020

    Hi there!
    At university, I didn't get that stuff into my head – thanks so much, now I understand much more!
    None the less, you work with numbers as data set.
    I'm trying to classify words – more specific: I have a set of over 1.000.000 OPAC-queries; I pre-classified about 3.000 of them intellectual – i took the query and labled a subject to it (for example query: subject heading: napoleon wars -> class: history or query: library-notation: NP 1200 -> class: history).
    Now I want to take these 3.000 pre-classified queries, train a neural network and classify the 1.000.000 OPAC-queries (I try to find patterns in the classes á la "If you study history you normaly search in this way, and if you study science you search in this way…").
    Is there a way to use words for classification in a neural network?
    Do I have to change the words into numbers?
    Or are there better ways to do this taks?

    Hope pt. 6 will come soon!:D
    Best wishes and greetings from Bavaria!

  • sentdex
    December 15, 2020

    Is there going to be a part 6?

  • sentdex
    December 15, 2020

    The sine wave fitting is so informative! Kudos on the animations

  • sentdex
    December 15, 2020

    Thanks so much for these videos.. your explanations are awesome!

  • sentdex
    December 15, 2020

    Can you pls the meaning of the weights in contexxt with neural network is the meaning of weights in neural network is same as weights in linear regression then here weights are showing the importance of input to the preactivation output i.e weights showing the importance of x on y in the form of y = wx + b or is the weights showing the impoertance of inputs to activation ouput i.e output = activation_function(y) and why we need to use a linear transfromation on input like y = wx+b before applying non linearity can't we just use non linearity on the raw input pls explain.

  • sentdex
    December 15, 2020

    I cannot thank u enough on that magnificent effort .

    I'm waiting the following parts

  • sentdex
    December 15, 2020

    This is not fair. After the 5 videos why you stopped. still Waiting for the next part. 🙇‍♂️

  • sentdex
    December 15, 2020

    Watched the series, will buy the ebook next

  • sentdex
    December 15, 2020

    Brilliant, just brilliant! 🙂

  • sentdex
    December 15, 2020

    you are a great teacher! is part 6 available? thanks!

  • sentdex
    December 15, 2020

    Please post the next part.

  • sentdex
    December 15, 2020

    Really thank youuuu for this amazing series of videos! I really enjoy the way you explain complex concepts and the visual demonstration is extremely helpful! Many thanks keep it up!

  • sentdex
    December 15, 2020

    I'm horribly waiting for the next episode… please don't make us wait longer! You're doing a great job and your effort is really appreciated.

  • sentdex
    December 15, 2020

    when is part 6 coming?!?!

  • sentdex
    December 15, 2020

    Which software do you use

  • sentdex
    December 15, 2020

    Hi, if i buy the book, would I be able to continue without having to wait for part 6? i.e. is all the content from part 6, part .. n in the book?

  • sentdex
    December 15, 2020

    When will the next tutorial come? 🙂

  • sentdex
    December 15, 2020

    Great series. Hope everything is okay and part 6 and beyond will get produced when you can!

  • sentdex
    December 15, 2020

    Which IDE do you use?

  • sentdex
    December 15, 2020

    This series (and the book) are incredible! Such an amazing teacher – I can't wait for part 6 🙂

  • sentdex
    December 15, 2020

    It has been 5 months :((

  • sentdex
    December 15, 2020

    11:11 I'm not really understanding why the red dot on the second neuron is going backwards.

  • sentdex
    December 15, 2020

    Dude, you're a legend. Bought the ebook Pre-Order yesterday, absolutely CANNOT WAIT for full release. My favourite thing about your videos, is your enthusiasm. For example, at 8:38, "What's so cool about ReLU is it's ALMOST linear, it's sooooo close to being linear, but yet that little itty-bitty bit of that rectified clipping at 0, is exactly what makes it powerful; as powerful as a sigmoid activation function, super fast, but this is what makes it work, and it's so cool! So WHY does it work??" Dude, I've never been so PUMPED to learn from someone with such enthusiasm in my LIFE. You take all the time you need to do this man, do it your way, and take your time, and you'll change the world. Thank you so much. Much love from Ireland. edit: spellings

Write a comment