Machine learning focuses on prediction, based on known properties learned from the training data. Data mining (which is the analysis step of Knowledge Discovery in Databases) focuses on the discovery of (previously) unknown properties on the data.
[Glossary (by google)](https://developers.google.com/machine-learning/glossary/)
Durk Kingma sur Twitter : about likelihood-based generative models(About) Durk Kingma sur Twitter
> "It is my personal belief is that sufficiently powerful likelihood-based generative models will usher in a new era of machine learning, allowing us to tackle important limitations of current machine learning, such as lacking data efficiency and generalization. [7/8]"
Cracking big data with statistical physics(About) > Models studied in statistical physics are mathematically equivalent to some of those in high-dimensional statistics.
> Statistical physics is often concerned with phase transitions, i.e., abrupt changes in behaviour. Interestingly, there is a deep correspondence between physical phases such as liquid, super-cooled liquid or glass, and solid, and regions of parameters for which a given data analysis task is algorithmically impossible, hard or easy
[1611.04228] Learning Sparse, Distributed Representations using the Hebbian Principle(About) The "fire together, wire together" Hebbian model is a central principle for learning in neuroscience, but surprisingly, it has found limited applicability in modern machine learning. In this paper, we take a first step towards bridging this gap, by developing flavors of competitive Hebbian learning which produce sparse, distributed neural codes using online adaptation with minimal tuning
Provable Algorithms for Machine Learning Problems by Rong Ge.(About) from the abstract:
Modern machine learning algorithms can extract useful information from text, images and videos. All these applications involve solving NP-hard problems in average case using heuristics. What properties of the input allow it to be solved effciently? Theoretically analyzing the heuristics is very challenging. Few results were known.
This thesis takes a different approach: we identify natural properties of the input, then design new algorithms that provably works assuming the input has these properties. We are able to give new, provable and sometimes practical algorithms for learning tasks related to text corpus, images and social networks.
...In theory, the assumptions in this thesis help us understand why intractable problems in machine learning can often be solved; in practice, the results suggest inherently new approaches for machine learning.