The theory of statistical learning has focused on variational objectives...
Large language models based on transformers have achieved great empirica...
To make sense of millions of raw data and represent them efficiently,
pr...
A core principle in statistical learning is that smoothness of target
fu...
Self-Supervised Learning (SSL) has emerged as the solution of choice to ...
Self-supervised learning (SSL) has emerged as a powerful framework to le...
Unsupervised representation learning aims at describing raw data efficie...
Applied mathematics and machine computations have raised a lot of hope s...
The workhorse of machine learning is stochastic gradient descent. To acc...
Classification is often the first problem described in introductory mach...
Machine learning approached through supervised learning requires expensi...
Discrete supervised learning problems such as classification are often
t...
We propose visual creations that put differences in algorithms and human...
This note explains a way to look at reproducing kernel Hilbert space for...
Annotating datasets is one of the main costs in nowadays supervised lear...
We propose a new form of human-machine interaction. It is a pictorial ga...