Book on Amazon
Личный блог о поездках (Россия, Крит, Норвегия, США, Атланта, Сан-Франциско, Кремниевая долина, Австралия), науке и технологиях (machine learning, computer science, data mining, information retrieval, семантический поиск, Semantic Web, программа Фулбрайта, Fulbright, Казанский федеральный университет), программировании (Java, Scala, R, Python), хобби (Quora, музыка, концерты, бренды часов, игры, автомобили, телевидение) и политике (Навальный, Путин, Медведев, Саакашвили, Ли Куан Ю, Брежнев).
Показаны сообщения с ярлыком машинное обучение. Показать все сообщения
Показаны сообщения с ярлыком машинное обучение. Показать все сообщения
четверг, 26 января 2017 г.
Deep Learning Book (2016)
"Written by three experts in the field, Deep Learning is the only comprehensive book on the subject." – Elon Musk, co-chair of OpenAI; cofounder and CEO of Tesla and SpaceX
Book on Amazon
Book on Amazon
суббота, 11 октября 2014 г.
Scalable tensor factorization: Ext-RESCAL 0.7 is out
I've published Ext-RESCAL 0.7 on GitHub. The version has critical fixes in using proper sparse matrix types (SciPy module) for representing tensor slices. In my current experiments, I could handle a tensor (derived from DBpedia 3.9) of ~ 6 million x 6 million x 1000 dimensions, including over 180 million non-zero values, on ~ 70GB RAM. To the best of my knowledge, this is the largest dataset, for which RESCAL has been used so far.
If you are interested in details of the problem, this software aims to solve, see the previous post on Machine Learning with Knowledge Graphs.
 |
| RESCAL factorization (taken from [Nickel, 2013]) |
If you are interested in details of the problem, this software aims to solve, see the previous post on Machine Learning with Knowledge Graphs.
пятница, 12 сентября 2014 г.
Highly Recommended Books for Machine Learning Researchers
Frankly speaking, there are many recommendations out there (e.g. see this thread and related threads on Quora). But, hoping to blend together academic and industry concerns, I would like to provide here recommendations for machine learning researchers made by only two people: Michael Jordan, a distinguished professor from University of Berkeley, and Bradford Cross, a founder of Prismatic.
M. Jordan's list
 |
| Recommended books as a background for machine learning |
Michael Jordan suggests for reading books on probability theory and statistics, optimization theory, information theory, and analysis.
The sources are as follows:
The full list of references is available here.
B. Cross' list
A couple of years ago, based on his experience, Bradford Cross gave a comprehensive list of the best resources on machine learning and the prerequisites in his blog ("Measuring measures"). According to him, these basics are essential:
Подписаться на:
Сообщения (Atom)