Explore >> Select a destination
|
You are here 
|
vladfeinberg.com | ||
| | | | |
akosiorek.github.io
|
|
| | | | | Machine learning is all about probability.To train a model, we typically tune its parameters to maximise the probability of the training dataset under the mo... | |
| | | | |
isaacslavitt.com
|
|
| | | | | [AI summary] The article discusses the German Tank Problem, a statistical estimation challenge where the goal is to infer the total number of tanks based on observed serial numbers, using Bayesian methods and MCMC libraries like Sampyl, PyMC3, and PyStan. | |
| | | | |
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... | |
| | | | |
www.nicktasios.nl
|
|
| | | In the Latent Diffusion Series of blog posts, I'm going through all components needed to train a latent diffusion model to generate random digits from the MNIST dataset. In the third, and last, post, | ||
