Section 4.2.0 - Introductory Writeups
Section 4.2.0.1 - Basic Writeups
Section 4.2.0.1.1 - Part 1 - Wikipedia - What is an ANN?
Section 4.2.0.1.2 - Part 2 - Asimov Institute - Cells and Layers of ANNs
Section 4.2.0.1.3 - Part 3 - Asimov Institute - Some examples of ANNs
Section 4.2.0.2 - Detailed Writeups
Section 4.2.0.2.1 - Part 1 - Textbook - David Kriesel - A Brief Introduction to Neural Networks
Section 4.2.0.2.2 - Part 2 - Textbook - Michael Nielsen - Neural Networks and Deep Learning
Section 4.2.0.2.3 - Part 3 - Edited by Kenji Suzuk - ANN: Architecture and Applications
Section 4.2.0.2.4 - Part 4 - Text Book - Simon Haykin - Neural Networks and Learning Machines
Section 4.2.0.2.5 - Part 5 - Online Text Book - Zhang,Lipton,Li,Smola - Dive Into Deep Learning
Section 4.2.0.2.6 - Part 6 - Complex-Valued Neural Networks
Section 4.2.0.2.6.1 - Part 1 - Trabelsi,Bilaniuk,Zhang,Serdyuk,Subramanian,Santos,Mehri,Rostamzadeh,Bengio, Pal - Deep Complex Networks
Section 4.2.0.2.6.2 - Part 2 - Thesis - Nitzan Guberman - On Complex Valued CNN's
Section 4.2.0.2.6.3 - Part 3 - Monning, Manandhar - Evaluation of Complex-Valued Neural Networks on Real-Valued Classification Tasks
Section 4.2.0.2.6.4 - Part 4 - Monning,Manandhar - Comparison of the Complex Valued and Real Valued Neural Networks Trained with Gradient Descent and Random Search Algorithms
Section 4.2.0.2.6.5 - Part 5 - El-Telbany,Refat - Complex-Valued Neural Networks Training: A Particle Swarm Optimization Strategy
Section 4.2.0.2.6.6 - Part 6 - Aizenberg - Complex-Valued Neural Networks II. Multi-Valued Neurons: Theory and Applications
Section 4.2.0.2.6.7 - Part 7 - Minin,Knoll,Zimmermann - Complex Valued Recurrent Neural Network: From Architecture to Training
Section 4.2.0.2.7 - Part 7 - Li,Xu,Taylot,Studer,Goldstein - Visualizing the Loss Landscape of Neural Networks
Section 4.2.1 - Feedforward Networks
Section 4.2.1.0 - Basic Writeup - Wikipedia - Feed Forward Neural Network
Section 4.2.1.1 - Neural Backprop
Section 4.2.1.1.0 - Basic Writeup - Wikipedia - Neural Back Propogation
Section 4.2.1.1.1 - Backprop
Section 4.2.1.1.1.0 - Introductory Writeups
Section 4.2.1.1.1.0.1 - Basic Writeup - Wikipedia - Backpropogation
Section 4.2.1.1.1.0.2 - Detailed Writeup - Rumelhart,Durbin,Golden,Chauvin - Backpropogation: The Basic Theory
Section 4.2.1.1.1.1 - Delta Rule
Section 4.2.1.1.1.2 - Chain Rule
Section 4.2.1.1.1.3 - Gauss–Newton algorithm
Section 4.2.1.1.2 - Cascade Correlation
Section 4.2.1.1.3 - Quickprop
Section 4.2.1.1.4 - Resilient backprop (RPROP)
Section 4.2.1.2 - Linear and Non-Linear
Section 4.2.1.2.0 - Basic Writeups
Section 4.2.1.2.0.1 - Part 1 - Unknown - Non-Linear Feedforward Control
Section 4.2.1.2.0.2 - Part 2 - Whitman - Linear Neural Networks
Section 4.2.1.2.0.3 - Part 3 - Grossberg - NonLinear Neural Networks
Section 4.2.1.2.1 - Radial Based Function (RBF) networks (Linear Neural Networks)
Section 4.2.1.2.1.0 - Introductory Writeups
Section 4.2.1.2.1.0.1 - Basic Writeup - Wikipedia - Radial Basis Function Network
Section 4.2.1.2.1.0.2 - Detailed Writeup - Orr - Introduction to Radial Based Function Networks
Section 4.2.1.3 - Perceptron
Section 4.2.1.4 - Adaline and Madaline
Section 4.2.1.5 - Higher Order Neural Networks
Section 4.2.1.5.0 - Introductory Writeups
Section 4.2.1.5.0.1 - Basic Writeup
Section 4.2.1.5.0.2 - Detailed Writeup - Gupta,Bukovsky,Homma,Solo,Hou - Fundamentals of Higher Order Neural Networks for Modeling and Simulation
Section 4.2.1.5.1 - Sigma-Pi Networks
Section 4.2.1.5.1.0 - Basic Writeup - Univ of Pretoria - High Order Neural Networks
Section 4.2.1.5.1.1 - Sigma-Pi-Sigma Networks
Section 4.2.1.5.2 - Pi-Sigma Networks
Section 4.2.1.5.2.0 - Basic Writeup - Univ of Pretoria - High Order Neural Networks
Section 4.2.1.5.2.1 - Jordan Pi-Sigma Network
Section 4.2.1.5.3 - Functional Link
Section 4.2.1.5.4 - Second Order
Section 4.2.1.5.5 - Product Unit
Section 4.2.1.6 - MLP: Multilayer perceptron
Section 4.2.1.6.0 - Introductory Writeups
Section 4.2.1.6.0.1 - Basic Writeups
Section 4.2.1.6.0.1.1 - Part 1 - Ujjwalkarn - A Quick Introduction oto Neural Networks
Section 4.2.1.6.0.1.2 - Part 2 - Wikipedia - Multilayer Perceptron
Section 4.2.1.6.0.2 - Detailed Writeup - Textbook Chapter 3 - Principe,Euliano,Lefebvre - Multilayer Perceptrons
Section 4.2.1.7 - Convolutional Neural Network
Section 4.2.1.7.0 - Introductory Writeups
Section 4.2.1.7.0.1 - Basic Writeup - Wikipedia - Convolutional Neural Network
Section 4.2.1.7.0.2 - Detailed Writeup - Wu - Convolutional Neural Networks
Section 4.2.1.7.1 - Design of CNN's
Section 4.2.1.7.2 - Building Blocks of CNN's
Section 4.2.1.7.3 - Intuitive Explanations and Demos of CNN's
Section 4.2.1.7.4 - Types of Convolutions
Section 4.2.1.7.4.0 - Basic Writeup - DeepLearning.net - Convolutional Arithmetic
Section 4.2.1.7.4.1 - Discrete Convolutions
Section 4.2.1.7.4.2 - Transposed Convolutions
Section 4.2.1.7.4.3 - Dilated Convolutions
Section 4.2.1.7.4.4 - Grouped Convolutions
Section 4.2.1.7.4.5 - Seperable Convolutions
Section 4.2.1.7.5 - Deep Convolutional Inverse Graphics Network
Section 4.2.1.7.6 - Convolutional Deep Q-networks
Section 4.2.1.7.7 - Convolutional Deep Belief Network
Section 4.2.1.8 - CMAC: Cerebellar Model Articulation Controller
Section 4.2.1.10 - Pure Classification only
Section 4.2.1.10.1 - LVQ: Learning Vector Quantization
Section 4.2.1.10.2 - PNN: Probabilistic Neural Network
Section 4.2.1.11 - Non Parametric Regression
Section 4.2.1.11.1 - GNN: General Regression Neural Network
Section 4.2.1.12 - Hinton Capsule Based
Section 4.2.1.12.0 - Introductory Writeups
Section 4.2.1.12.0.1 - Basic Writeup - Max Pechyonkin - Understanding Hinton's Capsule Networks: Intuition
Section 4.2.1.12.0.2 - Detailed Writeups
Section 4.2.1.12.0.2.1 - Part 1 - Wikipedia - Hinton's Capsule Neural Network
Section 4.2.1.12.0.2.2 - Part 2 - Hinton,Krizhevsky,Wang - Transforming Auto-Encoders
Section 4.2.1.13 - Extreme Learning Machine
Section 4.2.1.14 - Residual Network
Section 4.2.1.14.0 - Basic Writeup - Wikipedia - Residual Neural Network
Section 4.2.1.14.1 - Deep Residual
Section 4.2.1.14.2 - Highway Networks
Section 4.2.2 - Feedback or Recurrent Neural Networks
Section 4.2.2.0 - Basic Writeup - Wikipedia - Recurrent Neural Network
Section 4.2.2.1 - Neural Turing Machine
Section 4.2.2.2 - BAM: Bidirectional Associative Memory
Section 4.2.2.3 - Boltzman Machine
Section 4.2.2.3.0 - Introductory Writeups
Section 4.2.2.3.0.1 - Basic Writeup - Wikipedia - Boltzmann Machine
Section 4.2.2.3.0.2 - Detailed Writeup - Hinton - Boltzmann Machines
Section 4.2.2.3.1 - Restricted Boltzman Machine
Section 4.2.2.3.1.0 - Introductory Writeups
Section 4.2.2.3.1.0.1 - Basic Writeups
Section 4.2.2.3.1.0.1.1 - Part 1 - Skymind.ai - Restricted Boltzmann Machine
Section 4.2.2.3.1.0.1.2 - Part 2 - Wikipedia - Restricted Boltzmann Machine
Section 4.2.2.3.1.0.2 - Detailed Writeups
Section 4.2.2.3.1.0.2.1 - Part 1 - Deeplearning Net - Restricted Boltzmann Machines
Section 4.2.2.3.1.0.2.2 - Part 2 - Mont´ufar - Restricted Boltzmann Machines: Introduction and Review
Section 4.2.2.3.1.1 - Conditional Restricted Boltzman Machine
Section 4.2.2.3.1.2 - Mean Field Theory of Restricted Boltzman Machine
Section 4.2.2.3.1.3 - Deep Belief Networke
Section 4.2.2.3.2 - Deep Boltzman Machine
Section 4.2.2.3.3 - High Order Boltzman Machine
Section 4.2.2.3.4 - Non-Binary Units Boltzman Machine
Section 4.2.2.4 - Gated Recurrent Unit
Section 4.2.2.4.0 - Introductory Writeups
Section 4.2.2.4.0.1 - Basic Writeups
Section 4.2.2.4.0.1.1 - Part 1 - Wikipedia - Gated Recurrent Unit
Section 4.2.2.4.0.1.2 - Part 2 - Zhang,Lipton,Li,Smola - Dive Into Deep Learning: Gated Recurrent Unit
Section 4.2.2.4.0.2 - Detailed Writeup - Chung, Gulcehre, Cho, Bengio - Gated Feedback Recurrent Neural Networks
Section 4.2.2.4.1 - Deep Gate Recurrent Neural Network
Section 4.2.2.5 - Hopfield Network
Section 4.2.2.5.0 - Introductory Writeups
Section 4.2.2.5.0.1 - Basic Writeup - Wikipedia - Hopfield Network
Section 4.2.2.5.0.2 - Detailed Writeup - Textbook Chapter 13 - Rojas - Neural Networks: The Hopfield Model
Section 4.2.2.6 - Recurrent time series
Section 4.2.2.6.0 - Basic Writeup - Petnehazi - Recurrent Neural Networks for Time Series Forecasting
Section 4.2.2.6.1 - Long Short Term Memory (LSTM)
Section 4.2.2.6.1.0 - Introductory Writeups
Section 4.2.2.6.1.0 - Basic Writeups
Section 4.2.2.6.1.0.1.1 - Part 1 - Wikipedia - Long Short Term Memory
Section 4.2.2.6.1.0.1.2 - Part 2 - Skymind.ai - LSTM
Section 4.2.2.6.1.0.2 - Detailed Writeup - Hochreiter,Schmidhuber - Long Short-Term Memory
Section 4.2.2.6.2 - Simple Recurrent Networks
Section 4.2.2.6.2.1 - Elman Network
Section 4.2.2.6.2.2 - Jordan Network
Section 4.2.2.6.3 - FIR: Finite Impulse Response Neural Net
Section 4.2.2.6.4 - Real-time Recurrent Network
Section 4.2.2.6.5 - Recurrent Backprop
Section 4.2.2.6.6 - TDNN: Time Delay NN
Section 4.2.2.7 - Liquid State Machine
Section 4.2.2.8 - Echo State Network
Section 4.2.2.9 - Bidirectional Recurrent Neural Network
Section 4.2.3 - Memory Networks
Section 4.2.3.1 - Attention Mechanism
Section 4.2.3.1.0 - Basic Writeup
Section 4.2.3.1.0.1 - Part 1 - Skymind - Attention Mechanisms
Section 4.2.3.1.0.2 - Part 2 - Mahendra Venkatachalam - Attention In Neural Networks
Section 4.2.3.1.0.3 - Part 3 - Buomsoo Kim - Attention In Neural Networks - Part 1
Section 4.2.3.1.1 - Detailed Writeup - Zhang,Lipton,Li,Smola - Dive into Deep Learning: Attention Mechanism
Section 4.2.3.1.2 - Hierarchical Attention Networks
Section 4.2.3.1.3 - Graph Attention Networks
Section 4.2.3.1.4 - Transformer Attention Networks
Section 4.2.3.1.4.1 - Detailed Writeups
Section 4.2.3.1.4.1.1 - Part 1 - Zhang,Lipton,Li,Smola, - Transformer Attention Mechanism
Section 4.2.3.1.4.1.2 - Part 2 - Vaswani,Shazer,Parmar,Uszkoreit,Jones,Gomez,Kaiser - Attention is All You Need
Section 4.2.3.1.4.1.3 - Part 3 - Devlin,Chang,Lee,Toutanova - Bidirectional Encoder Representations from Transformer Attention Networks(BERT)
Section 4.2.3.1.4.1.4 - Part 4 - Dai,Yang,Yan,Carbonell,Le,Salakhutdinov - Transformer-XL: Attentitive Language Models Beyond a Fixed-Length Context
Section 4.2.3.1.4.1.5 - Part 5 - Yang,Dai,Yang,Carbonell,Salakhutdinov,Le - XLNet: Generalized Autoregressive Pretraining for Language Understanding
Section 4.2.4 - Competitive Networks
Section 4.2.4.0 - Basic Writeup - Wikipedia - Competitive Learning
Section 4.2.4.1 - Adaptive Resonance Theory
Section 4.2.4.2 - Counterpropagation
Section 4.2.4.3- Neocognitron
Section 4.2.4.4 - Vector Quantization
Section 4.2.4.4.0 - Basic Writeup - Vector Quantization
Section 4.2.4.4.1 - Grossberg Competitive Learning
Section 4.2.4.4.2 - Kohonen Self Organizing Maps
Section 4.2.4.4.3 - Conscience Competitive Learning
Section 4.2.4.5 - Self-Organizing Map
Section 4.2.4.5.0 - Basic Writeup - Wikipedia - Self Organizing Map
Section 4.2.4.5.1 - Kohonen Self Organizing Maps
Section 4.2.4.5.2 - Generative Topographics Map (GTM)
Section 4.2.4.5.3 - Local Linear
Section 4.2.4.6 - DCL: Differential Competitive Learning
Section 4.2.5 - Adversarial Networks
Section 4.2.5.1 - Generative Adversarial Networks
Section 4.2.5.1.0 - Introductory Writeups
Section 4.2.5.1.0.1 - Basic Writeups
Section 4.2.5.1.0.1.1 - Part 1 - Geeks For Geeks - Generative Adversarial Networks (GANS)
Section 4.2.5.1.0.1.2 - Part 2 - Fritz.ai - An Introduction to GANS
Section 4.2.5.1.0.1.3 - Part 3 - Hui - GAN Series (from the beginning to the end)
Section 4.2.5.1.0.2 - Detailed Writeups
Section 4.2.5.1.0.2.1 - Part 1 - Goodfellow,Abadie,Mirza,Xu,Farley,Ozair†,Courville,Bengio - Generative Adversarial Nets
Section 4.2.5.1.0.2.2 - Part 2 - Ali - Pros and Cons of GAN Evaluation Measures
Section 4.2.5.1.0.2.3 - Part 3 - Barrat,Sharma - Note on the Inception Score
Section 4.2.5.1.1 - Deep Convolutional GANs (DCGANs)
Section 4.2.5.1.2 - Conditional GANs (cGANs)
Section 4.2.5.1.2.0 - Detailed Writeup - Miraz,Osindero - Conditional GANs (cGANs)
Section 4.2.5.1.2.1 - InfoGAN
Section 4.2.5.1.2.2 - Auxillary classifier GAN
Section 4.2.5.1.2.3 - Semi-Supervised GAN
Section 4.2.5.1.3 - StackGAN
Section 4.2.5.1.4 - GAN Cost Functions and Loss
Section 4.2.5.1.4.1 - Wasserstein GANs(WGAN)
Section 4.2.5.1.4.2 - Least Squares GAN(LSGAN)
Section 4.2.5.1.4.3 - Energy Based GAN (EBGAN)
Section 4.2.5.1.4.4 - Boundary Equilibrium GAN(BEGAN)
Section 4.2.5.1.4.5 - Boundary Equilibrium GAN(BEGAN)
Section 4.2.5.1.4.6 - Relativistic GAN(R-Standard GAN, R-Average GAN)
Section 4.2.5.1.5 - Image Translation and Advanced GANs
Section 4.2.5.1.5.1 - Px2Pix GAN
Section 4.2.5.1.5.2 - CycleGAN
Section 4.2.5.1.5.3 - BigGAN
Section 4.2.5.1.5.4 - Progessively Growing GAN
Section 4.2.5.1.5.5 - StyleGAN
Section 4.2.6 - Deep Cognitive Models
Section 4.2.6.1 - Hierarchical Temporal Memory
Section 4.2.6.1.0 - Introductory Writeups
Section 4.2.6.1.0.1 - Basic Writeup - Wikipedia - Hierarchical Temporal Memory
Section 4.2.6.1.0.2 - Detailed Writeups
Section 4.2.6.1.0.2.1 - Part 1 - Hawkings,George - Hierarchical Temporal Memory
Section 4.2.6.1.0.2.2 - Part 2 - Mnatzaganian,Kudithipudi,Fokoue - A Mathematical Formalization of Hierarchical Temporal Memory’s Spatial Pooler
Section 4.2.6.2 - Hebbian
Section 4.2.6.2.0 - Basic Writeup - Wikipedia - Hebbian Theory
Section 4.2.6.2.1 - Hebbian Plasticity
Section 4.2.6.2.2 - Hebbian Learning
Section 4.2.6.2.3 - Spike Time Dependent Plasticity
Section 4.2.6.2.3.0 - Introductory Writeups
Section 4.2.6.2.3.0.1 - Basic Writeups
Section 4.2.6.2.3.0.1.1 - Part 1 - Wikipedia - Spike Timing Dependent Plasticity
Section 4.2.6.2.3.0.1.2 - Part 2 - Wikipedia - Spiking Neural Network
Section 4.2.6.2.3.0.1.3 - Part 3 - Pfieffer,Pfiel - Deep Learning With Spiking Neurons: Opportunities and Challenges
Section 4.2.6.2.3.0.2 - Detailed Writeups
Section 4.2.6.2.3.0.2.1 - Part 1 - A Slide Deck
Section 4.2.6.2.3.0.2.2 - Part 2 - Tavanaei,Ghodrati,Kheradpisheh,Masquelier,Maida - Deep Learning in Spike Neural Networks
Section 4.2.6.2.3.0.2.3 - Part 3 - Ponulak,Kasiński - Introduction to spiking neural networks: Information processing, learning and applications
Section 4.2.6.2.3.0.2.4 - Part 4 - Vreeken - Spriking Neural Networks, an introduction
Section 4.2.6.2.4 - Oja
Section 4.2.6.2.5 - Sanger or Generalized Hebbian
Section 4.2.6.2.6 - Generalized Differential Hebbian
Section 4.2.6.2.7 - BCM Theory
Section 4.2.7 - Autoencoders
Section 4.2.7.0 - Basic Writeup - Wikipedia - Autoencoder
Section 4.2.7.1 - Denoising autoencoder
Section 4.2.7.2 - Sparse autoencoder
Section 4.2.7.3 - Variational autoencoder (VAE)
Section 4.2.7.4 - Contractive autoencoder (CAE)
Section 4.2.7.5 - Bidirectional LSTM autoencoder
Section 4.2.7.6 - Bidirectional Encoder Representations from Transformer Attention Networks (BERT)
Section 4.2.8 - Autoassociators
Section 4.2.8.0 - Basic Writeup - Univ of Minnesota - Introduction to Neural Networks: Heteroassociation and Autoassociation
Section 4.2.8.1 - Generalized autoassociator
Section 4.2.8.2 - BSB: Brain State in a Box
Section 4.2.8.3 - Hopfield
Section 4.2.9 - Co-operative Neural Networks
Section 4.2.9.0 - Basic Writeup - Shrivastava,bart,Price,Dai,Dai,Aluru - Cooperative Neural Networks (CoNN)
Section 4.2.9.1 - Cooperative Evolution of Neural Ensembles
Section 4.2.10 - Siamese Neural Networks
Section 4.2.10.0 - Introductory Writeups
Section 4.2.10.0.1 - Basic Writeup - Wikipedia - Siamese Network
Section 4.2.10.0.2 - Detailed Writeup - Chopra,Hadsell,LeCun - Learning a Similarity Metric Discriminatively, with Application to Face Verification
Section 4.2.11 - Triplet Neural Networks
Section 4.2.12 - Activation Functions
Section 4.2.12.0 - Basic Writeup - Wikipedia - Activation Functions
Section 4.2.12.1 - Ridge Functions
Section 4.2.12.1.0 - Basic Writeup - Wikipedia - Ridge Functions
Section 4.2.12.1.1 - Step Functions
Section 4.2.12.1.1.1 - Heaveside (Binary) Functions
Section 4.2.12.1.2 - Linear Functions
Section 4.2.12.1.2.1 - Linear
Section 4.2.12.1.2.2 - Identity
Section 4.2.12.1.3 - Partly Linear Functions
Section 4.2.12.1.3.1 - Rectifier Based Linear Functions
Section 4.2.12.1.3.1.1 - Rectifier
Section 4.2.12.1.3.1.2 - Leaky Rectifier Based
Section 4.2.12.1.3.1.2.1 - Leaky Rectifier
Section 4.2.12.1.3.1.2.2 - Parametric Leaky Rectifier
Section 4.2.12.1.3.1.2.3 - Randomized Leaky Rectifier
Section 4.2.12.1.3.1.3 - Gaussian Error Rectifier
Section 4.2.12.1.3.1.4 - Sigmoid Rectifier
Section 4.2.12.1.3.1.5 - SoftPlus
Section 4.2.12.1.3.1.6 - Exponential Based
Section 4.2.12.1.3.1.6.1 - Exponential
Section 4.2.12.1.3.1.6.2 - Scaled Exponential
Section 4.2.12.1.3.2 - Softshrink
Section 4.2.12.1.3.3 - Adaptive Piecewise Linear
Section 4.2.12.1.3.4 - Long Short-Term Memory Unit Based
Section 4.2.12.1.3.5 - Bent Identity
Section 4.2.12.1.4 - Non-Linear Functions
Section 4.2.12.1.4.1 - Sigmoid Functions
Section 4.2.12.1.4.1.0 - Basic Writeup - Wikipedia - Sigmoid Functions
Section 4.2.12.1.4.1.1 - Logistic
Section 4.2.12.1.4.1.2 - Generalized Logistic
Section 4.2.12.1.4.1.3 - Gudermannian
Section 4.2.12.1.4.1.4 - Hyperbolic Tangent Based
Section 4.2.12.1.4.1.4.1 - TanH
Section 4.2.12.1.4.1.4.2 - Hard TanH
Section 4.2.12.1.4.1.4.3 - ArcTan
Section 4.2.12.1.4.1.5 - Error
Section 4.2.12.1.4.1.6 - SmoothStep
Section 4.2.12.1.4.1.7 - Softsign
Section 4.2.12.1.4.1.8 - Swish
Section 4.2.12.1.4.2 - Algebraic Functions
Section 4.2.12.1.4.2.1 - Square Non-Linearity
Section 4.2.12.1.4.3 - Exponential Functions
Section 4.2.12.1.4.3.1 - Soft Exponential
Section 4.2.12.1.4.3.2 - Softmax
Section 4.2.12.1.4.1 - Circular Functions
Section 4.2.12.1.4.1.1 - SinC
Section 4.2.12.2 - Radial Functions
Section 4.2.12.2.0 - Basic Writeup - Wikipedia - Radial Functions
Section 4.2.12.2.1 - Infinitely Smooth
Section 4.2.12.2.1.1 - Gaussian
Section 4.2.12.2.1.2 - Inverse Multi-Quadratic
Section 4.2.12.2.1.3 - Multi-Quadratic
Section 4.2.12.2.2 - Poly-harmonic Spline
Section 4.2.12.2.3 - Thin Plate Spline
Section 4.2.12.2.4 - Compactly Supported RBFs
Section 4.2.12.2.4.1 - Bump Function
Section 4.2.12.3 - Multi-Fold Functions
Section 4.2.12.3.0 - Basic Writeup - Wikipedia - Multi-Fold Functions
Section 4.2.12.3.1 - Linear Folds
Section 4.2.12.3.2 - Tree-Like Folds
Section 4.2.12.3.3 - Maxout
