How Convolutional Neural Networks Work
brohrer.github.io
How Convolutional Neural Networks Work
1–10 of 54 posts
Re: How Convolutional Neural Networks Work
#2Great explanation. Thanks for sharing.
Re: How Convolutional Neural Networks Work
#3Really great write up. Ive been trying to wrap my not too mathematically talented head around convolutional filters and this really helped in visualizing what is happening.
Re: How Convolutional Neural Networks Work
#4So ist works just like i thought it would. Why are CNN so hyped? Wasnt all this already known decades ago? Or is it just because we can afford the computing power?
Re: How Convolutional Neural Networks Work
#5So ist works just like i thought it would. Why are CNN so hyped? Wasnt all this already known decades ago? Or is it just because we can afford the computing power?
The underlying math was figured out a long time ago, but it's only been in recent years that we've had the computing power to test these out on lots of complicated, real-world classification problems, and had some incredible success.
Re: How Convolutional Neural Networks Work
#6So ist works just like i thought it would. Why are CNN so hyped? Wasnt all this already known decades ago? Or is it just because we can afford the computing power?
Computing power, but also some implementation tricks that turn out to make things a lot better.
For example, activation via ReLU instead of sigmoid/tanh significantly improves the performance of deep neural networks.
Then there's stuff like BatchNorm, Pooling, Dropout etc...
Re: How Convolutional Neural Networks Work
#7So ist works just like i thought it would. Why are CNN so hyped? Wasnt all this already known decades ago? Or is it just because we can afford the computing power?
1. Computing power
2. Data availability
3. Fast, large local storage
Re: How Convolutional Neural Networks Work
#8This is brilliant, so far one of the easiest to understand explanations.
Re: How Convolutional Neural Networks Work
#9So ist works just like i thought it would. Why are CNN so hyped? Wasnt all this already known decades ago? Or is it just because we can afford the computing power?
Decades ago I played around with neural nets but was frustrated because I either had to preprocess and normalize my inputs to the point where I didn't need a network anymore or I had to train a large network with so much data that it was not practical.
Having a cookbook approach with a catchy name and orders of magnitude more processing power have revived neural nets and now they are finally doing something useful.
Now everyone is jumping on the bandwagon so the field is progressing very quickly. Just because it's hyped doesn't mean it's not worth giving it a second look (although I'm still on the sidelines myself.)
Re: How Convolutional Neural Networks Work
#10Question: I have a database with 1.000.000 vehicle pictures, organized by make and model. What would be the easiest way to play with this data, so that I can train it to predict the make / model? I don't want to reinvent the wheel now so much tutorials are written and software is being released. What would be the easiest way to start?