Hands-On Meta Learning with Python

Description

Cover Title Page Copyright and Credits Dedication About Packt Contributors Table of Contents Preface Chapter 1: Introduction to Meta Learning Meta learning Meta learning and few-shot Types of meta learning Learning the metric space Learning the initializations Learning the optimizer Learning to learn gradient descent by gradient descent Optimization as a model for few-shot learning Summary Questions Further reading Chapter 2: Face and Audio Recognition Using Siamese Networks What are siamese networks? Architecture of siamese networks Applications of siamese networks Face recognition using siamese networks Building an audio recognition model using siamese networks Summary Questions Further readings Chapter 3: Prototypical Networks and Their Variants Prototypical networks Algorithm Performing classification using prototypical networks Gaussian prototypical network Algorithm Semi-prototypical networks Summary Questions Further reading Chapter 4: Relation and Matching Networks Using TensorFlow Relation networks Relation networks in one-shot learning Relation networks in few-shot learning Relation networks in zero-shot learning Loss function Building relation networks using TensorFlow Matching networks Embedding functions The support set embedding function (g) The query set embedding function (f) The architecture of matching networks Matching networks in TensorFlow Summary Questions Further reading Chapter 5: Memory-Augmented Neural Networks NTM Reading and writing in NTM Read operation Write operation Erase operation Add operation Addressing mechanisms Content-based addressing Location-based addressing Interpolation Convolution shift Sharpening Copy tasks using NTM Memory-augmented neural networks (MANN) Read and write operations Read operation Write operation Summary Questions Further reading Chapter 6: MAML and Its Variants MAML MAML algorithm MAML in supervised learning Building MAML from scratch Generate data points Single layer neural network Training using MAML MAML in reinforcement learning Adversarial meta learning FGSM ADML Building ADML from scratch Generating data points FGSM Single layer neural network Adversarial meta learning CAML CAML algorithm Summary Questions Further reading Chapter 7: Meta-SGD and Reptile Meta-SGD Meta-SGD for supervised learning Building Meta-SGD from scratch Generating data points Single layer neural network Meta-SGD Meta-SGD for reinforcement learning Reptile The Reptile algorithm Sine wave regression using Reptile Generating data points Two-layered neural network Reptile Summary Questions Further readings Chapter 8: Gradient Agreement as an Optimization Objective Gradient agreement as an optimization Weight calculation Algorithm Building gradient agreement algorithm with MAML Generating data points Single layer neural network Gradient agreement in MAML Summary Questions Further reading Chapter 9: Recent Advancements and Next Steps Task agnostic meta learning (TAML) Entropy maximization/reduction Algorithm Inequality minimization Inequality measures Gini coefficient Theil index Variance of algorithms Algorithm Meta imitation learning MIL algorithm CACTUs Task generation using CACTUs Learning to learn in concept space Key components Concept generator Concept discriminator Meta learner Loss function Concept discrimination loss Meta learning loss Algorithm Summary Questions Further reading Assessments Other Books You May Enjoy Index