From the course: Building Recommender Systems with Machine Learning and AI

Unlock this course with a free trial

Join today to access over 22,700 courses taught by industry experts.

CNN architectures

CNN architectures - Python Tutorial

From the course: Building Recommender Systems with Machine Learning and AI

Start my 1-month free trial Buy for my team

CNN architectures

“

- [Instructor] As I said, CNNs are very computationally intensive. They are very heavy in your CPU, your GPU, and your memory requirements. Shuffling all that data around and convolving it adds up really, really fast. Beyond that, there's a lot of what we call hyperparameters, a lot of different knobs and dials that you can adjust on CNNs. So in addition to the usual stuff, you can tune the topology of your neural network or whatever optimizer you use, or what loss function you use or what activation function you use. There are also choices to make about the kernel sizes, that is the the area that you actually convolve across. How many layers do you have? How many units do you have, and how much pooling do you do when you're reducing the image down? There's a lot of variants here. There are almost an infinite amount of possibilities for configuring a CNN, but often just obtaining the data to train your CNN is the hardest part. So for example, if you own a Tesla car, that's actually…

Contents