Theory of Neural Networks – Deep Learning Without Frameworks



Finally understand how deep learning and neural networks actually work. In this talk by Beau Carnes, you will learn the theory of neural networks. Instead of teaching about a framework such as Karas or TensorFlow, Beau gives an overview of the methods behind those frameworks.

First, he explaining the key concepts of deep learning. Then, he live codes a neural network using Python without using any frameworks. This will help you understand the concepts at a deeper level.

🐦 Beau Carnes on Twitter: https://twitter.com/carnesbeau

🔗 Beau’s Deep Learning course from Manning Publications: https://www.manning.com/livevideo/grokking-deep-learning-in-motion?a_aid=algmotion&a_bid=5d7bc0ba

Talk given at Moscow PythonConf++ 2018. Check out their YouTube channel: https://www.youtube.com/user/moscowdjangoru

Learn to code for free and get a developer job: https://www.freecodecamp.org

Read hundreds of articles on programming: https://medium.freecodecamp.org

And subscribe for new videos on technology every day: https://youtube.com/subscription_center?add_user=freecodecamp

source

This Post Has 24 Comments

  1. Norman Henderson

    Sure sounds like a technique used to flush ‘bad people’ out, who later on might be insignificant relatively. I know how you all do. Training the population to snoop on their own associates and the casually-known.

  2. Norman Henderson

    So Frameworks is used to automatically generate the relevance or irrelevance of the assumption?

  3. Timothy Schmidt

    Good talk overall, but the slide at 3:52 is incorrect. ML is one of the techniques used for AI, but AI also uses other techniques (eg: Search, Rule-Based Systems, Probability based decision making, etc.), so it would be more accurate to say AI is a superset of ML.

  4. Ryan L

    Great talk but the fact that none of his jokes fell made me uncomfortable lol

  5. martin

    Interesting talk. Thank you for sharing

  6. Nico Robin

    I don't understand how do you decide the value of the weight? .1, .2 ? How is this done?

  7. Carl Summers

    I didn't quite understand the part on negative reversal. So essentially if I have negative input and I'm multiplying it by the weight , how would I make it go into the positive direction? Would I, in this case, square the negative value with itself to receive a positive value? Any explanation on this would be great.

  8. Sam

    Hey great talk! Is there the transcript of the code anywhere online? That would help a lot. Thanks

  9. cinegraphics

    Who else was trying to clean up his monitor, only to find out that dirt spots are in fact in the video itself??

  10. venkatteja Raavi

    This video was shot based on grokking deep learning Text book by Andrew Trask. Have a look at the official text book. The explanations are so damn cool

  11. Qian Chen

    Thank you so much!! Finally I understand the intuition of the hidden layers.

  12. Business Opportunity in Ruvol

    I have invented a Board Game [still unpublished and not yet out in the market] that I believe is guaranteed to be as challenging and exciting as CHESS. I called it “RUVOL.”

    It is my hope that one day Ruvol may surpass chess as the “Number One Board Game in the World.”

    The weakness of chess is it always starts in fixed positions that the opening moves become “memorizable.” In fact, not a few have so mastered the moves that they can play against their opponents “blindfolded.” It is for this very reason that the great Bobby Fischer introduced his so-called “Fischer Random Chess,” where the starting position of the pieces is “randomized” to make the memorization of openings impracticable. Fortunately, it is also for this reason that I invented Ruvol where “every game” has been calculated to be a challenging one to play.

    HOW IS RUVOL PLAYED and HOW YOU CAN MONETIZE IT?

    I detailed everything in my YouTube video. Here is the link: https://www.youtube.com/watch?v=jcqth0m3-R0

    BIG MONEY POTENTIAL IN RUVOL!

    It is worthwhile to note that the people who play chess will be the same people who will play Ruvol. In my Google search, I learned there are around 800 million chess players in the world. Even just a small percentage of these 800 million is good enough to earn big money from Ruvol either as an ONLINE GAME BUSINESS or as a PHYSICAL PRODUCT DISTRIBUTOR.

    You may contact me at: rodolfovitangcol@gmail.com.

    Thanks and God bless!

    RODOLFO MARTIN VITANGCOL
    The Ruvol Inventor

  13. Jorgen B

    How many people work on large ai projects like Tesla’s AI and how much time does large scale machine learning projects take? Do you recommend any books that explains the comprehensive mathematical algorithms and code together in an image classifier?

  14. David Shook

    note the hand gestures have nothing to do with the content, just for distraction

Leave a Reply