Machine learning constitutes a vital role in Artificial intelligence and deals with the ability of machines to learn from the massive amount of data using knowledge representation, processing, and storing. Recently, machine learning has received great unprecedented popularity with the development of several new areas. The previously established research areas have also gained new momentum in big data analysis. The tremendous growth in the quantity of digital data, affordable computing resources, and optimization algorithms has enabled machine learning techniques for the breakthrough of artificial intelligence. For instance, large quantities of medical data are analyzed for diagnosis and treatment. The machine learning techniques analyze the medical data and determine the patterns in the bio-signals. They drive advances in healthcare and medical research.
The recent research on machine learning algorithms attempts to solve the following challenges, 1) Developing the machine learning algorithms that can computationally scale to Big data, 2) Designing algorithms that do not require large amounts of labeled data, 3) Designing a resource-efficient machine learning methods, and 4) developing a privacy preservation techniques for various applications.
Machine Learning Models: Supervised - Unsupervised - Semi-Supervised - Regression - Ensemble - Reinforcement
Deep Learning Models: Deep Neural Networks - Deep Recurrent Neural Networks - Deep Belief Networks - Deep Boltzmann Machine - Deep Autoencoder -Generative Neural Networks - Deep Ensemble Learning - Deep Reinforcement Learning - Convolutional Neural Networks- Transfer Learning - Extreme Learning Machines - Deep Generative Models - Dynamic Neural Networks - Radial Basis Function Networks - Long Short-Term Memory Networks - Restricted Boltzmann Machines - Self Organizing Maps - Transfer Reinforcement Learning - Multi-Goal Reinforcement Learning - Unsupervised Representation Learning - Distributional Reinforcement Learning -Extreme Multi-Label Classification - Generalized Few-Shot Classification - Multimodal Deep Learning - Quantum Machine Learning - One-Shot Learning - Hierarchical Reinforcement Learning - Multiple Instance Learning - Interpretable Machine Learning - Imitation Learning - Federated Learning - Active Learning - Few-Shot Learning - Meta-Learning - Representation Learning - Deep Cascade Learning- Explainable Deep Neural Networks - Evidential Deep Learning -Graph Representation Learning - Meta Reinforcement Learning - Graph Convolutional Networks - Hopfield Neural Networks - Quaternion Factorization Machines - Adversarial Machine Learning - Hyperbolic Deep Neural Networks - Few-Shot Class-Incremental Learning - Non-Local Graph Neural Networks -Distributed Active Learning - Triple Generative Adversarial Network - Shallow Broad Neural Network - Spiking Neural Networks - Bayesian Neural Networks - Word Embedding Models-Neural Machine Translation - Attention Mechanisms - Domain Adaptation - Data Augmentation - Image Augmentation - Text Augmentation -Neural Architecture Search - Hyperparameter Optimization - Neural Architecture Search - Feature Engineering
Applications: Natural Language Processing - Stream Processing - Recommendation Systems - Sentiment Analysis - Opinion Mining - Time Series Data Analysis - Medical Machine Learning - Disease Prediction - Multimedia - Stock Market Prediction - Cyber security - Pattern Recognition - Medical Imaging - Healthcare - Speech Recognition - Computer Vision - Malware Detection System - Intrusion Detection System - Intelligent Wireless Networks - Big Data Analytics - Intelligent Vehicular Networks -Autonomous Vehicles - Time Series Forecasting - Edge Intelligence - Cloud Computing - Internet of Vehicles - Semantic Similarity