Quantum Computing. Melanie Swan

Чтение книги онлайн.

СКАЧАТЬ 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

       9.4Challenges and Advances

       9.4.1Generalized learning

       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

       9.5Deep Learning Applications

       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)

       References

       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

       10.1.3Geometric deep learning

       10.2Standardized Methods for Quantum Computing

       10.2.1Standardized quantum computation tools

       10.2.2Standardized quantum computation algorithms

       10.2.3Quantum optimization

       10.2.4Quantum simulation

       10.2.5Examples of quantum machine learning

       References

       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

       11.3.4System criticality

       11.3.5Optimal control theory

       11.4Summary of the Spin-Glass Model

       11.5Spin-Glass Model: System Norm and Criticality

       11.6Detailed Description of the Spin-Glass Model

       11.6.1Spin glasses

       11.6.2Advanced model: p-Spherical spin glass

       11.6.3Applications of the spin-glass model: Loss optimization

       References

       СКАЧАТЬ