HackerTube

Neural Networks Demystified [Part 1: Data and Architecture]

Welch Labs3 HN recommenders · 2015–2018
838K views · tutorial · evergreen · Uploaded 2014-11-04

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.

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

Machine learning & deep learning

Watch on YouTube

4 comments from Hacker News

@film422015 · in “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]: [VIDEO] [3]: [LINK]

Strongly recommendsView on HN
@josso2016 · in “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]: [VIDEO]

RecommendsView on HN
@max_2016 · in “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 [VIDEO] - 2. Write basic Machine Learning code [LINK] - 3. Understand the Mathmatics involved [LINK] - 4. Get some important concepts, [LINK] - 5. Finnish off. [LINK]

RecommendsView on HN
@rayalez2018 · in “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

CitesView on HN