Efficient learning machines : theories, concepts, and applications for engineers and system designers
Machine learning techniques provide cost-effective alternatives to traditional methods for extracting underlying relationships between information and data and for predicting future events by processing existing information to train models. Efficient Learning Machines explores the major topics of ma...
Uloženo v:
| Hlavní autoři: | , |
|---|---|
| Médium: | E-kniha Kniha |
| Jazyk: | angličtina |
| Vydáno: |
Berkeley, CA
Apress Open
2015
Apress Springer Nature Apress L. P friendsof ED, Apress, ApressOpen |
| Vydání: | 1 |
| Edice: | The expert's voice in machine learning |
| Témata: | |
| ISBN: | 9781430259893, 1430259892, 9781430259909, 1430259906 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
Obsah:
- Intro -- Contents at a Glance -- Contents -- About the Authors -- About the Technical Reviewers -- Acknowledgments -- Chapter 1: Machine Learning -- Key Terminology -- Developing a Learning Machine -- Machine Learning Algorithms -- Popular Machine Learning Algorithms -- C4.5 -- k -Means -- Support Vector Machines -- Apriori -- Estimation Maximization -- PageRank -- AdaBoost (Adaptive Boosting) -- k -Nearest Neighbors -- Naive Bayes -- Classification and Regression Trees -- Challenging Problems in Data Mining Research -- Scaling Up for High-Dimensional Data and High-Speed Data Streams -- Mining Sequence Data and Time Series Data -- Mining Complex Knowledge from Complex Data -- Distributed Data Mining and Mining Multi-Agent Data -- Data Mining Process-Related Problems -- Security, Privacy, and Data Integrity -- Dealing with Nonstatic, Unbalanced, and Cost-Sensitive Data -- Summary -- References -- Chapter 2: Machine Learning and Knowledge Discovery -- Knowledge Discovery -- Classification -- Clustering -- Dimensionality Reduction -- Collaborative Filtering -- Machine Learning: Classification Algorithms -- Logistic Regression -- Random Forest -- Hidden Markov Model -- Multilayer Perceptron -- Machine Learning: Clustering Algorithms -- k -Means Clustering -- Fuzzy k -Means (Fuzzy c - Means) -- Streaming k -Means -- Streaming Step -- Ball K-Means Step -- Machine Learning: Dimensionality Reduction -- Singular Value Decomposition -- Principal Component Analysis -- Lanczos Algorithm -- Initialize -- Algorithm -- Machine Learning: Collaborative Filtering -- User-Based Collaborative Filtering -- Item-Based Collaborative Filtering -- Alternating Least Squares with Weighted- l -Regularization -- Machine Learning: Similarity Matrix -- Pearson Correlation Coefficient -- Spearman Rank Correlation Coefficient -- Euclidean Distance
- Swarm Intelligence -- Ant Colony Optimization Algorithm -- Particle Swarm Optimization -- Artificial Bee Colony Algorithm -- Bacterial Foraging Optimization Algorithm -- Artificial Immune System -- Distributed Management in Datacenters -- Workload Characterization -- Thermal Optimization -- Load Balancing -- Algorithm Model -- References -- Chapter 7: Deep Neural Networks -- Introducting ANNs -- Early ANN Structures -- Classical ANN -- ANN Training and the Backpropagation Algorithm -- DBN Overview -- Restricted Boltzmann Machines -- DNN-Related Research -- DNN Applications -- P arallel Implementations to Speed Up DNN Training -- Deep Networks Similar to DBN -- References -- Chapter 8: Cortical Algorithms -- Cortical Algorithm Primer -- Cortical Algorithm Structure -- Training of Cortical Algorithms -- Unsupervised Feedforward -- Supervised Feedback -- Weight Update -- The workflow for CA training is displayed in Figure 8-4 . -- Experimental Results -- Modified Cortical Algorithms Applied to Arabic Spoken Digits: Case Study -- Entropy-Based Weight Update Rule -- Experimental Validation -- References -- Chapter 9: Deep Learning -- Overview of Hierarchical Temporal Memory -- Hierarchical Temporal Memory Generations -- Sparse Distributed Representation -- Algorithmic Implementation -- Spatia l Poole r -- Temporal Pooler -- Related Work -- Overview of Spiking Neural Networks -- Hodgkin-Huxley Model -- Integrate-and-Fire Model -- Leaky Integrate-and-Fire Model -- Izhikevich Model -- Thorpe's Model -- Information Coding in SNN -- Learning in SNN -- SNN Variants and Extensions -- Evolving Spiking Neural Networks -- Reservoir-Based Evolving Spiking Neural Networks -- Dynamic Synaptic Evolving Spiking Neural Networks -- Probabilistic Spiking Neural Networks -- Conclusion -- References -- Chapter 10: Multiobjective Optimization -- Formal Definition
- Jaccard Similarity Coefficient -- Summary -- References -- Chapter 3: Support Vector Machines for Classification -- SVM from a Geometric Perspective -- SVM Main Properties -- Hard-Margin SVM -- Soft-Margin SVM -- Kernel SVM -- Multiclass SVM -- SVM with Imbalanced Datasets -- Improving SVM Computational Requirements -- Case Study of SVM for Handwriting Recognition -- Preprocessing -- Feature Extraction -- Hierarchical, Three-Stage SVM -- Experimental Results -- Complexity Analysis -- References -- Chapter 4: Support Vector Regression -- SVR Overview -- SVR: Concepts, Mathematical Model, and Graphical Representation -- Kernel SVR and Different Loss Functions: Mathematical Model and Graphical Representation -- Bayesian Linear Regression -- Asymmetrical SVR for Power Prediction: Case Study -- References -- Chapter 5: Hidden Markov Model -- Discrete Markov Process -- Definition 1 -- Definition 2 -- Definition 3 -- Introduction to the Hidden Markov Model -- Essentials of the Hidden Markov Model -- The Three Basic Problems of HMM -- Solutions to the Three Basic Problems of HMM -- Solution to Problem 1 -- Forward Algorithm -- Backward Algorithm -- Scaling -- Solution to Problem 2 -- Initialization -- Recursion -- Termination -- State Sequence Backtracking -- Solution to Problem 3 -- Continuous Observation HMM -- Multivariate Gaussian Mixture Model -- Example: Workload Phase Recognition -- Monitoring and Observations -- Workload and Phase -- Mixture Models for Phase Detection -- Sensor Block -- Model Reduction Block -- Emission Block -- Training Block -- Parameter Estimation Block -- Phase Prediction Model -- State Forecasting Block -- System Adaptation -- References -- Chapter 6: Bioinspired Computing: Swarm Intelligence -- Applications -- Evolvable Hardware -- Bioinspired Networking -- Datacenter Optimization -- Bioinspired Computing Algorithms
- Pareto Optimality -- Dominance Relationship -- Performance Measure -- Machine Learning: Evolutionary Algorithms -- Genetic Algorithm -- Genetic Programming -- Multiobjective Optimization: An Evolutionary Approach -- Weighted-Sum Approach -- Vector-Evaluated Genetic Algorithm -- Multiobjective Genetic Algorithm -- Niched Pareto Genetic Algorithm -- Nondominated Sorting Genetic Algorithm -- Strength Pareto Evolutionary Algorithm -- Strength of Solutions -- Fitness of P Solutions -- Clustering -- Strength Pareto Evolutionary Algorithm II -- Pareto Archived Evolutionary Strategy -- Pareto Envelope-Based Selection Algorithm -- Pareto Envelope-Based Selection Algorithm II -- Elitist Nondominated Sorting Genetic Algorithm -- Example: Multiobjective Optimization -- Objective Functions -- References -- Chapter 11: Machine Learning in Action: Examples -- Viable System Modeling -- Example 1: Workload Fingerprinting on a Compute Node -- Phase Determination -- Fingerprinting -- Size Attribute -- Phase Attribute -- Pattern Attribute -- Forecasting -- Example 2: Dynamic Energy Allocation -- Learning Process: Feature Selection -- Learning Process: Optimization Planning -- Learning Process: Monitoring -- Model Training: Procedure and Evaluation -- Example 3: System Approach to Intrusion Detection -- Modeling Scheme -- Observed (Emission) States -- Hidden States -- Intrusion Detection System Architecture -- Profiles and System Considerations -- Sensor Data Measurements -- Summary -- References -- Index