Пара интересных заметок с KDNuggets

[nick_marcevich2]

1. Опенсорсная С++ библиотека, реализующая алгоритмы machine learning.
Ссылка на kdnuggets: http://www.kdnuggets.com/2014/06/dlib-library-machine-learning.html
Ссылка на сайт библиотеки: http://dlib.net/, библиотека ml: http://dlib.net/ml.html





У них есть ещё раздел image processing, но тут, имхо, openCV вне конкуренции. ;-)

2. О распознавании вообще и в частности face recognition:
http://www.kdnuggets.com/2014/06/new-beginnings-facial-recognition.html

Любопытно:

In Ray Kurzweil’s book How to Create a Mind, it is argued that the human brain contains approximately 300 million ‘general pattern recognizers’ arranged in a hierarchical pattern. Input signals feed through various layers, and concepts are learned in an increasingly abstract sense until a new pattern is learned or an existing pattern recognized.

The closest parallel to this in machine learning are artificial neural networks (ANNs). ANNs use mind-inspired mechanics including simulated neurons and layering to learn concepts from experience (exposure to data). ANNs have been applied to a number of problems in pattern discovery including facial recognition but until recently have had limited success in real-world facial recognition systems.

This is now changing with the use of Deep Learning; a set of algorithms in machine learning that attempt to model high-level abstractions using an approach more closely aligned with how our minds recognize patterns. Using a large number of layers, so called Deep Neural Networks (DNNs) can mimic human learning by adjusting the strength of connections between simulated neurons within many layers, just as the human mind is believed to strengthen our understanding of a concept. Each layer can model an increasingly abstract concept built from the more basic concepts learned at earlier layers.

Интересно, обоснованна ли там эта цифра - 300 миллионов паттернов распознавания? :) А что алгоритмы уже приближаются по точности к распознаванию "вручную", а где-то и превосходят - это да.