rel="nofollow" href="#litres_trial_promo">9.1.1Why is deep learning called “deep”?
9.1.2Why is deep learning called “learning”?
9.1.3Big data is not smart data
9.1.4Types of deep learning networks
9.2Perceptron Processing Units
9.2.1Jaw line or square of color is a relevant feature?
9.3Technical Principles of Deep Learning Networks
9.3.1Logistic regression: s-curve functions
9.3.2Modular processing network node structure
9.3.3Optimization: Backpropagation and gradient descent
9.4.2Spin glass: Dark knowledge and adversarial networks
9.4.3Software: Nonlinear dimensionality reduction
9.4.4Software: Loss optimization and activation functions
9.4.5Hardware: Network structure and autonomous networks
9.5.1Object recognition (IDtech) (Deep learning 1.0)
9.5.2Pattern recognition (Deep learning 2.0)
9.5.3Forecasting, prediction, simulation (Deep learning 3.0)
Chapter 10Quantum Machine Learning
10.1Machine Learning, Information Geometry, and Geometric Deep Learning
10.1.1Machine learning as an n-dimensional computation graph
10.1.2Information geometry: Geometry as a selectable parameter
10.2Standardized Methods for Quantum Computing
10.2.1Standardized quantum computation tools
10.2.2Standardized quantum computation algorithms
10.2.5Examples of quantum machine learning
Part 4 Smart Network Field Theories
Chapter 11Model Field Theories: Neural Statistics and Spin Glass
11.1Summary of Statistical Neural Field Theory
11.2Neural Statistics: System Norm and Criticality
11.2.1Mean field theory describes stable equilibrium systems
11.2.2Statistical neural field theory describes system criticality
11.3Detailed Description of Statistical Neural Field Theory
11.3.1Master field equation for the neural system
11.3.2Markov random walk redefined as Markov random field
11.3.3Linear and nonlinear models of the system action
11.4Summary of the Spin-Glass Model
11.5Spin-Glass Model: System Norm and Criticality
11.6Detailed Description of the Spin-Glass Model
11.6.2Advanced model: p-Spherical spin glass
11.6.3Applications of the spin-glass model: Loss optimization
