Машинное обучение и искусственный интеллект — это уже не фантастика, а часть нашей жизни. Поисковые системы, умные ленты, распознавание голоса, лица, компьютерное зрение — уже сейчас машины во многом умнее нас, и сложно представить, насколько увеличится отрыв в будущем!
Но останутся ли у подобных умных алгоритмов слабые стороны? Можно ли будет обмануть искусственную нейронную сеть, свести с ума искусственный интеллект и разоблачить обман, созданный машиной?
Если вы всё ещё думаете что нейросети это сложно, посмотрите это видео. Самый полный и детальный разбор принципа работы нейронов и нейросетей с несколькими практическими примерами.
различные функции активации: ru.wikipedia.org/wiki/Функция_активации
В ролике использована композиция SizzleBird
Beyond A Dream soundcloud.com/sizzlebird/beyond-a-dream бесплатное распространение.
Поговорим о там как можно обучить сеть методом обратного распространения ошибки. В данном видео затронуты (но не раскрыты) такие темы как:
— производная youtu.be/qoHWa0eJHq4
— число е youtu.be/2Z2j4KqZ3QY
This talk discards hand-wavy pop-science metaphors and answers a simple question: from a computer science perspective, how can a quantum computer outperform a classical computer? Attendees will learn the following:
— Representing computation with basic linear algebra (matrices and vectors)
— The computational workings of qbits, superposition, and quantum logic gates
— Solving the Deutsch oracle problem: the simplest problem where a quantum computer outperforms classical methods
— Bonus topics: quantum entanglement and teleportation
The talk concludes with a live demonstration of quantum entanglement on a real-world quantum computer, and a demo of the Deutsch oracle problem implemented in Q# with the Microsoft Quantum Development Kit. This talk assumes no prerequisite knowledge, although comfort with basic linear algebra (matrices, vectors, matrix multiplication) will ease understanding.
— Video timeline (thanks to user «noonesperfect»)
0:36 Question 1
1:13 Answer 1
1:29 Introduction to tetration
3:37 How exponentiation works in tetration
6:10 Python program for power tower iterations
8:40 Question 2
9:32 Python Program regarding question 2
10:37 Answer 2 and explanation
13:18 Power tower for infinite size converges or not? (Thumbnail question)
15:21 Question 3
16:28 Footage of Grants setup arrangement problem due to construction-work back at home.
16:49 Answer 3 and explanation
17:40 Checking logic behind 2 different problems of power towers whose answer converges to the same value (Is it even possible?)
19:42 Checking same logic using Desmos graph tool i.e. Cobweb Graph (Desmos graph link in description)
28:12 Question 4
28:51 Questions from audience tweets
29:15 Knuths Up Arrow Notation and Grahams Number (Check Numberphile video in description)
32:32 Answer 4 and explanation
37:29 Homework/Challenge Puzzle
39:20 Thumbnail question power tower logic
40:55 Audience questions from twitter
41:45 Power tower for complex numbers/Fractal set
45:19 Brainteaser
48:06 More questions from tweets
53:17 Notes for lock-down series in Grants Tweeter
— The live question setup with stats on-screen is powered by Itempool. itempool.com/
If you want to contribute translated subtitles or to help review those that have already been made by others and need approval, you can click the gear icon in the video and go to subtitles/cc, then «add subtitles/cc». I really appreciate those who do this, as it helps make the lessons accessible to more people.
— 3blue1brown is a channel about animating math, in all senses of the word animate. And you know the drill with YouTube, if you want to stay posted on new videos, subscribe: 3b1b.co/subscribe
From the statisticians forecasting sports scores to the intelligent bots beating human poker players, Adam Kucharski traces the scientific origins of the worlds best gambling strategies.
Watch the Q