Luis Serrano
A friendly introduction to neural networks and deep learning.
This is a follow up to the Introduction to Machine Learning video.
https://www.youtube.com/watch?v=IpGxLWOIZy4
Note: In this tutorial I use natural logarithms. If you used logarithms base 10, you may get different answers that I got, although at the end it doesn’t matter, since using a different base for the logarithm just scales all the logarithms by a constant.
Source
Luis great.
Luis Great. how to get degree from Udacity University?
How can the linear combination of two linear curve becomes becomes higher degree curve ?? Video Time stamp 29:47
best video explaining neural networks
Hi Luis can you share the alogirth or code please.. And can you tell how you worked out the probabilities for the red point in blue area is 0.1
I believe one can only teach subject if he/she understand the subject and this is what Luis proved. Very simple and crisp clear explanation.
Thanks for this video, it's very well explained
The best video so far, explaining Deep Learning to mere mortals
Its great, congratulations, Ive never watched an explanation like this. It is awesome.
amazing simply superb , I will listen to what ever topic you post
lmao… 5:20 thought it was a scary alien robot. 5:31 Neural networks are a lot scarier than an alien robot loll. so true
20:41 is the final -log answer right??
You lost me at the probability, why would it be less or more probable depending on it's position, doesn't make sense
Thank-you.
You made my day, I thought there is no hope to understand these sophisticated topics, but you made it simple, easy, and even more detailed than the others, Thank you sooooo much Luis, I subscribed to your channel already 🙂
why not log_e or ln? little bit frustrating at this point
Deep Learning: Convolutional Neural Networks in Python
> Understand how convolution can be applied to image effects.
> Understand how convolution helps image classification.
> Implement a convolutional neural network in Theano
> Implement a convolutional neural network in TensorFlow.
http://bit.ly/2lKMSjv
Fantastic explanation!
If I understood your method, you compute how far a point from the line (above + , and below -). Then map it to a probability. If this true, we should subtract the bias instead of adding it. Otherwise, we will never get a negative number.
Thank you.. very insightful
very good intro to DNN. i like it
I'm stuck here: 22:29 where did you get the 2x + 7y and what is the 4 value that you compare their sum for? I mean, where did you get that the line is 4 = 2x + 7y?
Awsome… it is very easy to understand. Thank you.
Thank you Luis Serrano! Friendly and helpful introduction!! But I still got one question… maybe somebody reading this can help me? how is x and y defined? by where it is in the (blue or red) region? how is the blue or red region defined then? I don't get the relation between point and region. 😐
Great explanation, again! Thank you!
Nice Explanation
Now I know how to make a deep neural network to defeat Google DeepMind. I will add a sixth hidden layer!
A lot scarier than that :-). Great! 🙂
Very well explained
how come w1*(linear equation) + w2*(linear equation) + bias = non-linear equation?
I missed this one earlier. But again a great explanation of the shape of the classifiers ?.Thanks Ton
Outstanding video. You are a gifted educator.
Very clear explanation. I understand things I didn't understand before. Thanks!