The Artificial Intelligence (AI) has become a crucial field that drives innovation and transformation across a range of sectors. The Big Data has driven the development of algorithms and models for AI increasingly sophisticated. Machine learning, artificial neural networks, natural language processing (NLP), computer vision, big data processing and reinforcement learning are key areas of AI that enable the automation of complex tasks. This Course in Artificial Intelligence for Programmers is justified by the need to train programmers and developers who can design and implement efficient AI solutions that tackle complex real-world problems.
Sector-specific
AI Development
35 hours
Artificial Intelligence for Programmers
AI Development
35 hours
Introduction
Objectives
-
Understanding the concepts and principles of the Machine Learning and the various techniques and algorithms.
-
Mastering the design and training in Artificial Neural Networks.
-
Applying Natural Language Processing for classification tasks, text generation and sentiment analysis.
-
To develop skills in computer vision for the detection, recognition and classification of objects in images.
-
Apply the Big Data in the context of Artificial Intelligence and using tools such as Hadoop and Spark.
-
Optimising AI models by evaluating metrics, selecting features and preventing overfitting.
-
Mastering the Reinforcement Learning and apply it in areas such as games, robotics and optimisation resources.
Table of Contents
TEACHING UNIT 1. MACHINE LEARNING
Machine Learning
Types of machine learning
Algorithms and machine learning models
Evaluation metrics in machine learning
Regularisation and feature selection in machine learning
TEACHING UNIT 2. ARTIFICIAL NEURAL NETWORKS (ANN)
Artificial Neural Networks (ANN)
Structure and architecture
Activation functions
RNA training
Convolutional Neural Networks (CNNs) and their applications
Recurrent Neural Networks (RNN) and their application
Generative Adversarial Networks (GANs) and their application
TEACHING UNIT 3. NATURAL LANGUAGE PROCESSING (NLP)
Fundamentals of Natural Language Processing (NLP)
Representation of language in NLP
Feature extraction in PLN
Sequence-based NLP models
NLP models for specific tasks
Applications of PLN
TEACHING UNIT 4. COMPUTER VISION
Computer vision
Image pre-processing and transformation
Object detection and recognition
Image segmentation and classification
Machine vision applications
TEACHING UNIT 5. BIG DATA PROCESSING IN ARTIFICIAL INTELLIGENCE
Big Data in Artificial Intelligence
Distributed storage and processing
Technologies and tools for processing big data
Extracting knowledge from big data
Machine Learning in Big Data
TEACHING UNIT 6. OPTIMISATION AND TUNING OF AI MODELS
Evaluation of models and performance metrics
Hyperparameter optimisation
Adjustment and techniques for preventing overfitting
Dimensionality reduction techniques
Fitting and assembly of models
TEACHING UNIT 7. REINFORCEMENT LEARNING
Reinforcement learning
Agents and environments in reinforcement learning
Reinforcement learning methods
Exploration and exploitation in reinforcement learning
Reinforcement learning applications
TEACHING UNIT 8. DEPLOYMENT AND PRODUCTION OF AI MODELS
Data preparation for model deployment
Design and implementation of AI services
Monitoring and evaluation of models in production
Updating and maintaining AI models
Scalability and performance in the deployment of AI models
More related courses
Sector-specific
Sector-specific
Sector-specific