For anyone interested in how neuroscience data can be transformed into
knowledge via computational models, our new book "Data-Driven
Computational Neuroscience. Machine Learning and Statistical Models"
from Cambridge University Press is available from your favourite
bookseller in hardback, and ebook.
https://www.cambridge.org/core/books/datadriven-computational-neuroscience/1D528620B04385EFBDDCBDD3F5C1C485
/Data-driven computational neuroscience facilitates the transformation
of data into insights into the structure and functions of the brain.
This introduction for researchers and graduate students is the first
in-depth, self-contained comprehensive treatment of statistical and
machine learning methods for neuroscience. The methods are demonstrated
through case studies of real problems to empower readers to build their
own solutions. The corresponding models are learned with open source
software. The book covers a wide variety of methods, including
supervised classification with non-probabilistic models
(nearest-neighbors, classification trees, rule induction, artificial
neural networks and support vector machines) and probabilistic models
(discriminant analysis, logistic regression and Bayesian network
classifiers), meta-classifiers, multi-dimensional classifiers and
feature subset selection methods. Other parts of the book are devoted to
association discovery with probabilistic graphical models (Bayesian
networks and Markov networks) and spatial statistics with stochastic
point processes (complete spatial randomness and cluster, regular and
Gibbs processes). All cellular, structural, functional, medical and
behavioral neuroscience levels are considered. /
“This book represents an excellent opportunity for neuroscientists from
all fields to be introduced to this fascinating world of data-driven
computational neuroscience, expertly guided by the authors. Presented in
an easily accessible way to those who are not experts in the field, the
book provides us with an outstanding text dealing with the multiple
applications in modern neuroscience of statistical and computational
models learned from data.”*-Javier DeFelipe**, *Instituto Cajal, Consejo
Superior de Investigaciones Científicas (Spain)
“Data-Driven Computational Neuroscience is an outstanding treatment of
modern statistical data analysis and machine learning for neuroscience.
Working throughout from a set of real world use-cases, the text is a
hands on comprehensive presentation of technique and analysis and treats
many important but less well-known aspects of the practice.”*-Michael
Hawrylycz, *Allen Institute for Brain Science (USA)
"In our world of Big Brain Initiatives and Big Data, this encompassing
book provides the much-needed bridge between these two “Bigs”.
Data-driven computational and statistical methods are admirably
presented and exemplified, providing new insights on fundamental
challenges such as classifying neurons into types, uncovering the
neuronal code and unveiling principles of brain-connectivity. This book
is a must." -*Idan Segev, *The Edmond and Lily Safra Centre for Brain
Sciences, The Hebrew University of Jerusalem (Israel)
“With admirable zeal, Bielza and Larrañaga have digested and summarized
an entire field, the machine learning methods in computational
neuroscience. The critical importance of computational tools to analyze
neural data and decipher the neural code has been emphasized by the US
and international brain initiatives and this book provides a sure and
solid step in this direction.”*-Rafael Yuste, *Columbia University (USA)
Thanks!
Pedro Larrañaga and Concha Bielza
--
Prof. Pedro Larrañaga
Department of Artificial Intelligence
Technical University of Madrid
Campus de Montegancedo, s/n
28660 Boadilla del Monte
Madrid
tel: +34 91 06 72896
http://cig.fi.upm.es/CIGmembers/pedro-larranaga
_______________________________________________
uai mailing list
uai@engr.orst.edu
https://it.engineering.oregonstate.edu/mailman/listinfo/uai
