What is a Neural Network - Ep. 2 (Deep Learning SIMPLIFIED)

With plenty of machine learning tools currently available, why would you ever choose an artificial neural network over all the rest? This clip and the next could open your eyes to their awesome capabilities! You'll get a closer look at neural nets without any of the math or code - just what they are and how they work. Soon you'll understand why they are such a powerful tool!

Deep Learning TV on

Deep Learning is primarily about neural networks, where a network is an interconnected web of nodes and edges. Neural nets were designed to perform complex tasks, such as the task of placing objects into categories based on a few attributes. This process, known as classification, is the focus of our series.

Classification involves taking a set of objects and some data features that describe them, and placing them into categories. This is done by a classifier which takes the data features as input and assigns a value (typically between 0 and 1) to each object; this is called firing or activation; a high score means one class and a low score means another. There are many different types of classifiers such as Logistic Regression, Support Vector Machine (SVM), and Naïve Bayes. If you have used any of these tools before, which one is your favorite? Please comment.

Neural nets are highly structured networks, and have three kinds of layers - an input, an output, and so called hidden layers, which refer to any layers between the input and the output layers. Each node (also called a neuron) in the hidden and output layers has a classifier. The input neurons first receive the data features of the object. After processing the data, they send their output to the first hidden layer. The hidden layer processes this output and sends the results to the next hidden layer. This continues until the data reaches the final output layer, where the output value determines the object's classification. This entire process is known as Forward Propagation, or Forward prop. The scores at the output layer determine which class a set of inputs belongs to.

Links:

Have you worked with neural nets before? If not, is this clear so far? Please comment.
Neural nets are sometimes called a Multilayer Perceptron or MLP. This is a little confusing since the perceptron refers to one of the original neural networks, which had limited activation capabilities. However, the term has stuck - your typical vanilla neural net is referred to as an MLP.

Before a neuron fires its output to the next neuron in the network, it must first process the input. To do so, it performs a basic calculation with the input and two other numbers, referred to as the weight and the bias. These two numbers are changed as the neural network is trained on a set of test samples. If the accuracy is low, the weight and bias numbers are tweaked slightly until the accuracy slowly improves. Once the neural network is properly trained, its accuracy can be as high as 95%.

Credits:
Nickey Pickorita (YouTube art) -
Isabel Descutner (Voice) -
Dan Partynski (Copy Editing) -
Jagannath Rajagopal (Creator, Producer and Director) -

[TheMrGoodkind]

As a deaf programmer, I was really excited that you captioned episode 1. Could you please caption the other episodes?

[DeepLearningTV]

Hey all! This is the first topic in the series - Deep Learning starts and ends with Neural Networks. Enjoy :-)

[slidenerd]

that was the most badass explanation for neural networks that i ever saw online, damn you are good!

[shashank.tripathi]

The most simplified explanation I have ever found on net, textbook, videos or tutorials, very well organized, and each line of this video answers the questions I have been asking everyone, looking everyone, I blame myself for not finding your channel earlier. Thank you, keep up the good work, community needs you!

[FahimMahmoodMir]

Out of all those geeky videos and simple to complex mathematical explanation this video is one of the best for a guy who is looking for concept rather mathematical foundation. Thanks for this beautiful video.

[adityawi]

Wow! I finally understand why training loops needed. Very clear explanation. Thank you so much.

[jbulatao]

one of the best explanations of neural networks I've heard so far. well done.

[DeepLearningTV]

My two favorite resources are Michael Nielsen's book and Andrew Ng's class. Links in the description above. All the best!

[sescalaster]

I need to use neural networks for analyzing hyperspectral reflectance data from measurements made on plant tissue. This helps understanding what I'm against. Thank you.

[rhapsody]

4:22 minor correction here: the inputs of a neuron arent modified by the weights, they are multiplied by the weights and that produces some output, you can not modify inputs, you can only modify weights during the training

[Jimmy.]

Just starting to follow this series, you have a really nice voice :)
Thank you for the video, I believe those who new of Machine Learning concept will able to understand the concept easier.

[PulseCodeMusic]

Just learning this stuff out of curiosity really... mostly about the way our brains work, so its good to see the concepts presented in an accessible way :)

[caycewilliams-west]

the best explanation of DL you'll ever see.

[hieudt]

About training, Neural Network very like Fuzzy Inference sys combine with ACO algorithm, both of them need huge input to high accuracy output.

[anirbandutta]

I rarely subscribe to channels.But subscribed to this, because the guys are doing a tremendous job.

[shinable]

Those videos are super!!! Why don't you produce more videos?

[ritiksinha]

She is awesome, short and sweet explanations, Thanks a lot

[timothywise]

Wow...neural networks work a lot like a computational fluid dynamics model. Forward propagation schemes like subsonic flows, and I would wager there is a backward propagation like in supersonic flow. This is neat!

[jessicameeks]

Thank you so much for these. Perfect amount of information. Everything else I’ve found is either too simple or too complex.

[chandrasekaranramasamy]

Simple presentation for NN. Easy to understand I prescribe this for my students to go through. Thank you All