Specialize in artificial vision applied to Robotics and progress in your professional career with this Postgraduate diploma"

Far from science fiction, this program aimed at Computer Science professionals is oriented to provide all the necessary knowledge for the student to be able to project any idea to be developed in Artificial Intelligence or to work in Robotics projects, especially in the field of visual perception systems.

In this way, the teaching team specialized in this area will guide the students through the algorithmic bases that support its operation, its applications, advantages and limitations. To do this, during the 6 months of this online Postgraduate diploma, a theoretical-practical approach will be applied in which, through examples, the students will find environments with robots, but without losing sight of the relevance to understand the machine learning techniques to be used.

Although artificial vision is one of the most complex fields of Robotics, the multimedia material offered by this program will facilitate its learning. Thus, students will be able to acquire the main vision techniques based on learning systems, particularly the use of neural networks, which have revolutionized the way in which machine vision is used today. Likewise, in this program the student will learn the most advanced tools to be able to develop in the field of artificial vision for Robotics, both at a theoretical and practical level.

An excellent opportunity for graduates who wish to progress in their professional field under the guidance of the best specialists and with quality teaching, which allows access to all the content from the first day and a Relearning system, based on the reiteration of content, which in turn facilitates learning and knowledge consolidation.

Join a 100% online program and apply advanced Artificial Intelligence techniques on Intelligent Agents in your projects”

This Postgraduate diploma in Robot Visual Perception Systems with Machine Learning contains the most complete and up-to-date program on the market. The most important features include: 

• Development of case studies presented by experts in robotic engineering
• The graphic, schematic, and practical contents which provide scientific and practical information on the disciplines that are essential for professional practice
• Practical exercises where self-assessment can be used to improve learning
• Its special emphasis on innovative methodologies
• Theoretical lessons, questions to the expert, debate forums on controversial topics, and individual reflection assignments
• Content that is accessible from any fixed or portable device with an Internet connection

Unleash your full potential in this Postgraduate diploma and learn in a simple way to identify the new fields of application of generative neural networks”

The program’s teaching staff includes professionals from the sector who contribute their work experience to this educational program, as well as renowned specialists from leading societies and prestigious universities.

Its multimedia content, developed with the latest educational technology, will allow the professional a situated and contextual learning, that is, a simulated environment that will provide an immersive education programmed to prepare in real situations.

This program is designed around Problem-Based Learning, whereby the professionals must try to solve the different professional practice situations that arise throughout the program. This will be done with the help of an innovative system of interactive videos made by renowned experts.

This Postgraduate diploma will allow you to reach a high level of mastery of the algorithms used in the creation of robots"

An excellent opportunity for you to implement your projects in the area of Robotics"

The study plan of this Postgraduate diploma, which consists of 450 teaching hours, is divided into three modules in which Artificial Intelligence and its application in robots and softbots, to analyze all the techniques involved in the development of artificial vision and the essential tools for its development. The videos in detail and the rest of the multimedia material that the students will find in the virtual platform will complement this extensive program.

Enroll in this Postgraduate diploma and acquire advanced learning in Deep Learning through tools such as Google IColab”

Module 1. Intelligent Agents. Application of Artificial Intelligence to Robots and Softbots

1.1. Intelligent Agents and Artificial Intelligence

1.1.1. Intelligent Robots. Artificial Intelligence
1.1.2. Intelligent Agents

1.1.2.1. Hardware Agents. Robots
1.1.2.2. Software Agents. Softbots

1.1.3. Robotics Applications

1.2. Brain-Algorithm Connection

1.2.1. Biological Inspiration of Artificial Intelligence
1.2.2. Reasoning Implemented in Algorithms. Typology
1.2.3. Explainability of Results in Artificial Intelligence Algorithms
1.2.4. Evolution of Algorithms up to Deep Learning

1.3. Search Algorithms in the Solution Space

1.3.1. Elements in Solution Space Searches
1.3.2. Solution Search Algorithms in Artificial Intelligence Problems
1.3.3. Applications of Search and Optimization Algorithms
1.3.4. Search Algorithms Applied to Machine Learning

1.4. Machine Learning

1.4.1. Machine Learning
1.4.2. Supervised Learning Algorithms
1.4.3. Unsupervised Learning Algorithms
1.4.4. Reinforcement Learning Algorithms

1.5. Supervised Learning

1.5.1. Supervised Learning Methods
1.5.2. Decision Trees for Classification
1.5.3. Support Vector Machines
1.5.4. Artificial Neural Networks
1.5.5. Applications of Supervised Learning

1.6. Unsupervised Learning

1.6.1. Unsupervised Learning
1.6.2. Kohonen Networks
1.6.3. Self-Organizing Maps
1.6.4. K-Means Algorithm

1.7. Reinforcement Learning

1.7.1. Reinforcement Learning
1.7.2. Agents Based on Markov Processes
1.7.3. Reinforcement Learning Algorithms
1.7.4. Reinforcement Learning Applied to Robotics

1.8. Artificial Neural Networks and Deep Learning

1.8.1. Artificial Neural Networks. Typology
1.8.2. Applications of Neural Networks
1.8.3. Transformation from Machine Learning to Deep Learning
1.8.4. Deep Learning Applications

1.9. Probabilistic Inference

1.9.1. Probabilistic Inference
1.9.2. Types of Inference and Method Definition
1.9.3. Bayesian Inference as a Case Study
1.9.4. Nonparametric Inference Techniques
1.9.5. Gaussian Filters

1.10. From Theory to Practice: Developing an Intelligent Robotic Agent

1.10.1. Inclusion of Supervised Learning Modules in a Robotic Agent
1.10.2. Inclusion of Reinforcement Learning Modules in a Robotic Agent
1.10.3. Architecture of a Robotic Agent Controlled by Artificial Intelligence
1.10.4. Professional Tools for the Implementation of the Intelligent Agent
1.10.5. Phases of the Implementation of AI Algorithms in Robotic Agents

Module 2. Artificial Vision Techniques in Robotics: Image Processing and Analysis

2.1. Computer Vision

2.1.1. Computer Vision
2.1.2. Elements of a Computer Vision System
2.1.3. Mathematical Tools

2.2. Optical Sensors for Robotics

2.2.1. Passive Optical Sensors
2.2.2. Active Optical Sensors
2.2.3. Non-Optical Sensors

2.3. Image Acquisition

2.3.1. Image Representation
2.3.2. Color Space
2.3.3. Digitizing Process

2.4. Image Geometry

2.4.1. Lens Models
2.4.2. Camera Models
2.4.3. Camera Calibration

2.5. Mathematical Tools

2.5.1. Histogram of an Image
2.5.2. Convolution
2.5.3. Fourier Transform

2.6. Image Preprocessing

2.6.1. Noise Analysis
2.6.2. Image Smoothing
2.6.3. Image Enhancement

2.7. Image Segmentation

2.7.1. Contour-Based Techniques
2.7.3. Histogram-Based Techniques
2.7.4. Morphological Operations

2.8. Image Feature Detection

2.8.1. Point of Interest Detection
2.8.2. Feature Descriptors
2.8.3. Feature Matching

2.9. 3D Vision Systems

2.9.1. 3D Perception
2.9.2. Feature Matching between Images
2.9.3. Multiple View Geometry

2.10. Computer Vision based Localization

2.10.1. The Robot Localization Problem
2.10.2. Visual Odometry
2.10.3. Sensory Fusion

Module 3. Robot Visual Perception Systems with Automatic Learning

3.1. Unsupervised Learning Methods applied to Computer Vision

3.1.1. Clustering
3.1.2. PCA
3.1.3. Nearest Neighbors
3.1.4. Similarity and Matrix Decomposition

3.2. Supervised Learning Methods Applied to Computer Vision

3.2.1. “Bag of Words” Concept
3.2.2. Support Vector Machine
3.2.3. Latent Dirichlet Allocation
3.2.4. Neural Networks

3.3. Deep Neural Networks: Structures, Backbones and Transfer Learning

3.3.1. Feature Generating Layers

3.3.3.1. VGG
3.3.3.2. DenseNet
3.3.3.3. ResNet
3.3.3.4. Inception
3.3.3.5. GoogleNet

3.3.2. Transfer Learning
3.3.3. Data. Preparation for Training

3.4. Computer Vision with Deep Learning I: Detection and Segmentation

3.4.1. YOLO and SSD Differences and Similarities
3.4.2. Unet
3.4.3. Other Structures

3.5. Computer Vision with Deep Learning II: Generative Adversarial Networks

3.5.1. Image Super-Resolution Using GAN
3.5.2. Creation of Realistic Images
3.5.3. Scene Understanding

3.6. Learning Techniques for Localization and Mapping in Mobile Robotics

3.6.1. Loop Closure Detection and Relocation
3.6.2. Magic Leap. Super Point and Super Glue
3.6.3. Depth from Monocular

3.7. Bayesian Inference and 3D Modeling

3.7.1. Bayesian Models and “Classical” Learning
3.7.2. Implicit Surfaces with Gaussian Processes (GPIS)
3.7.3. 3D Segmentation Using GPIS
3.7.4. Neural Networks for 3D Surface Modeling

3.8. End-to-End Applications of Deep Neural Networks

3.8.1. End-to-End System. Example of Person Identification
3.8.2. Object Manipulation with Visual Sensors
3.8.3. Motion Generation and Planning with Visual Sensors

3.9. Cloud Technologies to Accelerate the Development of Deep Learning Algorithms

3.9.1. Use of GPUs for Deep Learning
3.9.2. Agile Development with Google IColab
3.9.3. Remote GPUs, Google Cloud and AWS

3.10. Deployment of Neural Networks in Real Applications

3.10.1. Embedded Systems
3.10.2. Deployment of Neural Networks. Use
3.10.3. Network Optimizations in Deployment, Example with TensorR

Master the use of Python and Tensorflow, key tools in the field of Robotics. Click and register now”