Plays via YouTube's privacy-enhanced embed

Neural Networks Demystified [Part 1: Data and Architecture]

Name: Neural Networks Demystified [Part 1: Data and Architecture]
Description: The first of a short series by Welch Labs on building a complete neural network in Python. It introduces the data and the architecture of a simple network before later parts cover forward propagation, gradient descent, and backpropagation.

Welch Labs

3 videos recommended on HN

YouTube

3 HN users recommended this tutorial3 months2015–2018 score 3.5

Years with an HN recommendation, 2007–2026

HN commenters point beginners to this series as one of the clearest short walkthroughs of how neural networks and backpropagation work.

The first of a short series by Welch Labs on building a complete neural network in Python. It introduces the data and the architecture of a simple network before later parts cover forward propagation, gradient descent, and backpropagation.

“One of the clearest walkthroughs I've seen online is a short series of very short videos by Stephen C Welch [2] [3].” (HN, 2015)

1 strong recommendations · 2 recommendations · 1 citations · Tutorials · intro

Machine learning & deep learning Tutorials AI, Machine Learning & Data

4 Hacker News comments

From the HN archive; up to 20 kept per video, favoring different commenters. Recommendations first.

@film42 Feb 2015 Strongly recommends

on HN thread Beginning deep learning with 500 lines of Julia

The gist of this is really the Backpropagation algorithm [1]. It appears as though everything else is a means to detect when to stop. One of the clearest walkthroughs I've seen online is a short series of very short videos by Stephen C Welch [2] [3]. If you're interested in this space, start with him. [1]: [link] [2]: [this video] [3]: [link]

Clear, short video series walking through backpropagation.

View on Hacker News

@josso Apr 2016 Recommends

on HN thread Google has started a video series on machine learning and I can understand it

I also recommend Welch Labs’ Neural Network Demystified-series[0]. It is a combination of the Coursera course and the YouTube videos. It get’s into some of the math, while still keeping it basic. [0]: [this video]

Series covering some math while keeping it basic.

View on Hacker News

@max_ Jun 2016 Recommends

on HN thread Ask HN: From programming to AI, how?

Hello, my background is just like yours. Assuming you are a total noob I learned that AI is not like programming, where anyone with basic knowledge of computation can dive in. You can NOT just learn AI by reading other people's code. Its like Physics, there are solid principles you need to understand before you get in. The point: AI does not come with the "batteries included". If you are in deed a noob you MUST learn the prerequisites. Follow these steps in order and I guarantee you will be competent with AI in six months tops.(from my past experience) - 1. Know what AI actually is [this video] - 2. Write basic Machine Learning code [link] - 3. Understand the Mathmatics involved [link] - 4. Get some important concepts, [link] - 5. Finnish off. [link]

First step in a learning path: what AI actually is.

View on Hacker News

Citations, criticism and jokes

@rayalez Feb 2018 Cites it

on HN thread How to learn Deep Learning in 6 months

Good post. I want to add several great resources. - Grokking Deep Learning [link] This is a fantastic book that assumes no prerequisites other than knowing python, and takes you through the fundamentals of DL. It has very intuitive and easy to follow explanations, and doesn't use any libraries other than NumPy, so you're building the whole thing yourself, from scratch. - Deep Learning With Python [link] This is kind of the opposite of the previous one, it doesn't go into math and theory, instead it guides you through building several practical projects with a very simple to use DL library(keras). It's a great way to gain practical experience in addition to theory from the previous book. Also has no prerequisites other than python, and makes it very easy to get started. - 3blue1brown videos on neural networks: [link] Extremely brilliant high-level concise overview of how ANNs work. I highly recommend you get started here. You should also check out his videos on calulus and linear algebra, they're fantastic way to learn the math you need. - Khan Academy videos - one of the easiest ways to learn the math prerequisites. Calculus: [link] Linear Algebra: [link] Probability and Statistics: [link] - Hands-On Machine Learning with Scikit-Learn and TensorFlow [link] I haven't read this one yet, but it looks very promising, and a lot of people seem to find it very useful. - Andrew Ng's Coursera course [link] Everyone knows about this one, I just think every article on AI resources shoul

View on Hacker News