Explore >> Select a destination
|
You are here 
|
vladfeinberg.com | ||
| | | | |
fanpu.io
|
|
| | | | | Deep learning is currently dominated by parametric models, which are models with a fixed number of parameters regardless of the size of the training dataset. Examples include linear regression models and neural networks. However, it's good to occasionally take a step back and remember that that is not all there is. Non-parametric models like k-NN, decision trees, or kernel density estimation don't rely on a fixed set of weights, but instead grow in complexity based on the size of the data. In this post we'll talk about Gaussian processes, a conceptually important, but in my opinion under-appreciated non-parametric approach with deep connections with modern-day neural networks. An intersting motivating fact which we will eventually show is that neural network... | |
| | | | |
erikbern.com
|
|
| | | | | I made a New Year's resolution: every plot I make during 2018 will contain uncertainty estimates. Nine months in and I have learned a lot, so I put together a summary of some of the most useful methods. | |
| | | | |
www.djmannion.net
|
|
| | | | | Data are sometimes on a circular scale, such as the angle of an oriented stimulus, and the analysis of such data often needs to take this circularity into account. Here, we will look at how we can use PyMC to fit a model to circular data. | |
| | | | |
www.v7labs.com
|
|
| | | What are Generative Adversarial Networks and how do they work? Learn about GANs architecture and model training, and explore the most popular generative models variants and their limitations. | ||
