000			01809ntdaa2200289 ab4500
999			_c25059 _d25059
003			EC-UPSE
005			20200819073347.0
006			a||||g ||i| 00| 0
008			140501s9999 mx ||||f |||| 00| 0 spa d
020			_a9781787125933
040			_aUPSE
041			_aspa
082			_a006.31 _bRASp
100			_917264 _aRaschka, Sebastian _eautor
245			_aPython machine learning. Machine learning and deep learning whit Python, scikit-learn and TensorFlow
250			_aSecond edition
260			_aBirmingham (Inglaterra): _bPackt Publishing _c2017
300			_a595 páginas _c(23x19 cm)
336			_2rdacontent _atext _btxt
337			_2rdamedia _ano mediado _bn
338			_2rdacarrier _avolumen _bnc
505			_aGiving computers the ability to learn from data.-- Training simple machine learning algorithms for classification.-- A tour of machine learning classifiers using scikit-learn.-- Building good training sets - data preprocessing.-- Compressing data via dimensionality reduction.-- Learning best practices for madel evaluation and hyperparameter tuning.-- Combining different model for ensamble learning.-- Embedding a machine learning model into a web application.-- Prediicting continuous target variables with regression analysis.-- Working with unlabiled data - clustering analysis.-- Implementing a multilayer artificial neural network from scratch.-- Parallelizing neural nentwork training with ternsorflow.-- Classifying images with deep convolutional neural networks.-- Modeling sequential data using recurrent neural networks.-- Introducing sequential data.-- RNNs for modeling sequenses.-- Implement a multiplayer RNN for sequence modeling in tensorflow
650		0	_912916 _aMECANICA
690			_aA16
700			_917265 _aMirjalili, Vahid _eautor
942			_2ddc _c1