000			a
999			_c30861 _d30861
008			220627b xxu||||| |||| 00| 0 eng d
020			_a9781108494939
082			_a006.32 _bMEH
100			_aMehlig, Bernhard
245			_aMachine learning with neural networks : an introduction for scientists and engineers
260			_bCambridge University Press, _c2022 _aCambridge :
300			_aix, 249 p. ; _bill., _c26 cm
365			_b39.99 _cGBP _d100.50
504			_aIncludes bibliographical references and index.
520			_aThis modern and self-contained book offers a clear and accessible introduction to the important topic of machine learning with neural networks. In addition to describing the mathematical principles of the topic, and its historical evolution, strong connections are drawn with underlying methods from statistical physics and current applications within science and engineering. Closely based around a well-established undergraduate course, this pedagogical text provides a solid understanding of the key aspects of modern machine learning with artificial neural networks, for students in physics, mathematics, and engineering. Numerous exercises expand and reinforce key concepts within the book and allow students to hone their programming skills. Frequent references to current research develop a detailed perspective on the state-of-the-art in machine learning research.
650			_aMachine learning
650			_aNeural networks
650			_aComputer science
650			_aActivation Function
650			_a Backpropagation
650			_aCentral-limit theorem
650			_a Cross-talk term
650			_a Decision boundary
650			_a Energy function
650			_aFeed-forward network
650			_aHidden neuron
650			_aHopfield network
650			_aImage Net
650			_aMarkov chain
650			_a Mean-field theory
650			_aNoise level
650			_aOutput neuron
650			_aPrinciple component
650			_aQ-table
650			_aResidwal network
650			_aStochastic gradient descent
650			_aVanishing gradient
650			_a Winning neoron
650			_aXOR problem
650			_aBoltzmann Machines
942			_2ddc _cBK