Revolutionize the technology sector thanks to this Master's Degree in Deep Learning”

The rapid technological evolution of recent years has meant that the self-driving vehicle, the early diagnosis of serious illnesses through high-precision imaging devices or facial recognition with mobile applications are not so far away. Thus, at present, these emerging innovations seek to improve the precision of automatisms and improve the quality of the results obtained.

A scenario, where the IT professional who must have exhaustive knowledge about Deep Learning plays a determining role, being also able to take another step in this race in the sector to create authentic Artificial Intelligence. For this reason, TECH has created this 12-month Master's Degree with the most advanced and current syllabus, prepared by true experts in this field.

A program with a theoretical-practical perspective that will lead students to acquire intensive learning about mathematical fundamentals, the construction of neural networks, model customization, and training with TensorFlow. A breadth of content that will be much easier to assimilate thanks to the video summaries of each topic, the videos in focus the specialized readings and the case studies. Likewise, with the Relearningsystem, used by TECH, the computer scientist will progress more naturally through this program, consolidating the new concepts more easily, thus reducing the long hours of study.

A university education that focuses on the knowledge that will make the student grow professionally, who also wants to make a first-level academic option compatible with their daily activities. And it is that all you need is a digital device with an internet connection to access this degree at the academic forefront at any time.

Succeed with your AI projects in sectors such as the automotive, finance or medical sectors with the teaching provided by TECH”

This Master's Degree in Deep Learning contains the most complete and up-to-date program on the market. The most important features include:

• The development of practical cases presented by experts in Data Engineer and Data Scientist
• The graphic, schematic and practical contents of the book provide technical and practical information on those 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 for 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

Delve whenever you want into the Hugging Face transformer libraries and other natural language processing tools to apply to vision problems”

The program’s teaching staff includes professionals from 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 provide the professional with situated and contextual learning, i.e., a simulated environment that will provide an immersive education designed to learn in real situations.

The design of this program focuses on Problem-Based Learning, by means of which the professional must try to solve different professional practice situations that are presented throughout the academic course. For this purpose, the student will be assisted by an innovative interactive video system created by renowned experts.

You have an advanced agenda in Deep Learning, 24 hours a day, from any digital device with an internet connection"

A 12-month Master's Degree with the application of Deep Learning techniques in real problems"

The study plan of this university program will take students on an academic journey that goes from the mathematical foundations of Deep Learning, its principles, the training of deep neural networks, the visualization of results and the evaluation of Deep Learning models. An exhaustive content, complemented by numerous innovative teaching resources that make up the Virtual Library of this program.

With the Relearning system you will say goodbye to long hours of study and you will acquire a much more effective and simple learning”

Module 1. Deep Learning Fundamentals

1.1. Functions and Derivatives

1.1.1. Linear Functions
1.1.2. Partial Derivative
1.1.3. Higher Order Derivatives

1.2. Multiple Nested Functions

1.2.1. Compound Functions
1.2.2. Innverse Functions
1.2.3. Recessive Functions

1.3. Chain Rule

1.3.1. Function Derivatives Nested
1.3.2. Derivatives of Compound Functions
1.3.3. Function Derivatives Inverse

1.4. Functions with Multiple Entries

1.4.1. Multi-variable Functions
1.4.2. Vectorial Functions
1.4.3. Matrix Functions

1.5. Derivatives of Functions with Multiple Entries

1.5.1. Partial Derivative
1.5.2. Directional Derivatives
1.5.3. Mixed Derivatives

1.6. Functions with Multiple Entries Diseases

1.6.1. Vectorial Linear Functions
1.6.2. Vectorial Non-Linear Functions
1.6.3. Vectorial of Matrix Functions

1.7. Creating New Functions From Existing Functions

1.7.1. Functions Sum
1.7.2. Functions Product
1.7.3. Functions Composition

1.8. Derivatives of Functions with Multiple Vectorial Entries

1.8.1. Function Derivatives Lineal
1.8.2. Function Derivatives Non-linear
1.8.3. Derivatives of Compound Functions

1.9. Funciones Vectoriales and their Derivatives: Always Go One Step Further

1.9.1. Directional Derivatives
1.9.2. Mixed Derivatives
1.9.3. Matriix Derivatives

1.10. Backward Pass

1.10.1. Error Propagation
1.10.2. Application of Update Rules
1.10.3. Parameter Optimization

Module 2. Deep Learning Principles

2.1. Supervised Learning

2.1.1. Supervised Learning Machines
2.1.2. Uses of Supervised Learning
2.1.3. Differences between Supervised and Unsupervised Learning

2.2. Supervised Learning Models

2.2.1. Linear Models
2.2.2. Models of Decision Trees
2.2.3. Models of Neural Networks

2.3. Linear Regression

2.3.1. Simple Linear Regression
2.3.2. Multiple Linear Regression
2.3.3. Regression Analysis

2.4. Model Training

2.4.1. Batch Learning
2.4.2. Online Learning
2.4.3. Optimization Methods

2.5. Model Evaluation Training Set Versus Test Set

2.5.1. Evaluation Metrics
2.5.2. Cross Validation
2.5.3. Comparison of Data Sets

2.6. Model Evaluation The Code

2.6.1. Prediction Generation
2.6.2. Error Analysis
2.6.3. Evaluation Metrics

2.7. Variable Analysis

2.7.1. Identification of Relevant Variables
2.7.2. Correlation Analysis
2.7.3. Regression Analysis

2.8. Explainability of Neural Network Models

2.8.1. Interpretive Model
2.8.2. Visualization Methods
2.8.3. Evaluation Methods

2.9. Optimization

2.9.1. Optimization Methods
2.9.2. Regularization Techniques
2.9.3. The Use of Graphics

2.10. Hyper-Parameters

2.10.1. Selection of Hyper-Parameters
2.10.2. Paramters Search
2.10.3. Hyper-Parameters Adjustment

Module 3. Neural networks, the basis of Deep Learning

3.1. Deep Learning

3.1.1. Types of Learning Foundations
3.1.2. Applications of Deep Learning
3.1.3. Hyper-Parameters Advantages and Disadvantages of Deep Learning

3.2. Surgery

3.2.1. Summary
3.2.2. Product
3.2.3. Transfer

3.3. Layers

3.3.1. Entry Layer
3.3.2. Hidden Layer
3.3.3. Out Layer

3.4. Layer Union and Operations

3.4.1. Architecture Design
3.4.2. Layer Connection
3.4.3. Forward Propagation

3.5. First Neural Network Construction

3.5.1. Network Design
3.5.2. Weight Establishment
3.5.3. Network Training

3.6. Trainer and Optimizer

3.6.1. Optimizer Selection
3.6.2. Establishment of a Loss Function
3.6.3. Metric Establishment

3.7. Applicaation of Neural Network Principles

3.7.1. Activation Functions
3.7.2. Backwards Propagation
3.7.3. Parameter Adjustment

3.8. From Biological Neurons to Artificial Ones

3.8.1. Functioning of a Biological Neuron
3.8.2. Knowledge Transfer to Artificial Neurons
3.8.3. Establish Relationships Between the Two

3.9. Implementation of MLP (Multilayer Perceptron) with Keras

3.9.1. Definition of the Structure of Networks
3.9.2. Model Compilation
3.9.3. Model Training

3.10. Hyperparameters of Fine tuning of Neural Networks

3.10.1. Selection of Activation Function
3.10.2. Establishing relearning rate
3.10.3. Weight Adjustment

Module 4. Training of Deep Neural Networks

4.1. Gradient Problems

4.1.1. Gradient Optimization Techniques
4.1.2. Stochastic Gradients
4.1.3. Weight Initialization Techniques

4.2. Reuse of Pretrained Layers

4.2.1. Transfer of Learning Training
4.2.2. Feature Extraction
4.2.3. Deep Learning

4.3. Optimizers

4.3.1. Stochastic Gradient Descent Optimizers
4.3.2. Adam and RMSprop Optimizers
4.3.3. Moment Optimizers

4.4. Learning Rate Programming

4.4.1. Control of Machine Learning Rate
4.4.2. Learning Cycles
4.4.3. Softening Terms

4.5. Overfitting

4.5.1. Cross Validation
4.5.2. Regularization
4.5.3. Evaluation Metrics

4.6. Guideline Practices

4.6.1. Model Design
4.6.2. Material Selection and Evaluation Paramters
4.6.3. Hypothesis Testing

4.7. Transfer Learning

4.7.1. Transfer of Learning Training
4.7.2. Feature Extraction
4.7.3. Deep Learning

4.8. Data Augmentation

4.8.1. Image Transformation
4.8.2. Generating Synthethic Data
4.8.3. Text Transformation

4.9. Practical Application of Transfer Learning

4.9.1. Transfer of Learning Training
4.9.2. Feature Extraction
4.9.3. Deep Learning

4.10. Regularization

4.10.1. L1 and L2
4.10.2. Regularization by Maximum Entropy
4.10.3. Dropout

Module 5. Customization of Models and training with TensorFlow

5.1. TensorFlow

5.1.1. Use of TensorFlow Library
5.1.2. TensorFlow Training Models
5.1.3. TensorFlow Graphic Operations

5.2. TensorFlow and NumPy

5.2.1. NumPy Computer Environment for TensorFlow
5.2.2. Use of NumPy Arrays with TensorFlow
5.2.3. NumPy Operations for TensorFlow Graphics

5.3. Customization of Training Models and Algorithms

5.3.1. Construction of Personalized TensorFlow Models
5.3.2. Management of Training Parameters
5.3.3. Use Optimization Techniques for Training

5.4. TensorFlow Functions and Graphics

5.4.1. TensorFlow Functions
5.4.2. Use Graph for Model Training
5.4.3. Optimization of Graphics with TensorFlow Operations

5.5. Load and Processing with TensorFlow Data

5.5.1. Load Groups with TensorFlow Data
5.5.2. Processing with TensorFlow Data
5.5.3. Using TensorFlow Tools for Data Manipulations

5.6. API tf.data

5.6.1. Using the tf.data API for Data Processing
5.6.2. Building Data Streams with tf.data
5.6.3. Using the Keras Preprocessing API for Model raining

5.7. TFRecord Format

5.7.1. Using the tf.data API for Data Processing
5.7.2. Loading TFRecord Files with TensorFlow
5.7.3. Using TFRecord files for Model Training

5.8. Keras Preprocessing Layers

5.8.1. Using the Keras Preprocessing API
5.8.2. Building Preprocessing Pipeline with Keras
5.8.3. Using the Keras Preprocessing API for Model raining

5.9. TensorFlow Datasets Project

5.9.1. Using TensorFlow Datasets for Data Loading
5.9.2. Processing with TensorFlow Data Datasets
5.9.3. Using TensorFlow Datasets for model training

5.10. Building a Deep Learning Application with TensorFlow. Practical Application

5.10.1. Building a Deep Learning Application with TensorFlow
5.10.2. TensorFlow Training Models
5.10.3. Use of the Application for the Prediction of Results

Module 6. Deep Computer Vision with Convolutional Neural Networks

6.1. Visual Cortex Architecture

6.1.1. Functions of the Visual Cortex
6.1.2. Computational Vision Theory
6.1.3. Image Processing Models

6.2. Convolution Layers

6.2.1. Reuse of Weights in Convolution
6.2.2. Convolution2D
6.2.3. Activation Functions

6.3. Pooling Layers and Implementing Pooling Layers with Keras

6.3.1. Pooling y Striding
6.3.2. Flattening
6.3.3. Types of Pooling

6.4. CNN Architecture

6.4.1. VGG Architecture
6.4.2. AlexNet Architecture
6.4.3. ResNet Architecture

6.5. Implementation of a ResNet-34 CNN using Keras

6.5.1. Weight Initialization
6.5.2. Input Layer Definition
6.5.3. Definition of the Exits

6.6. Using Pretrained Keras Models

6.6.1. Characteristics of Pretrained Models
6.6.2. Uses of Pretrained Models
6.6.3. Advantages of Pretrained Models

6.7. Pretrained Models for Transfer Learning

6.7.1. Transfer Learning
6.7.2. Transfer Learning Process
6.7.3. Transfer Learning Process

6.8. Classification and Location in Deep Computer Vision

6.8.1. Image Classification
6.8.2. Locating Objects in Images
6.8.3. Object Detection

6.9. Object Detection of Objects and Tracking

6.9.1. Objects Detection Methods
6.9.2. Object Tracking algorithms
6.9.3. Tracing and Localization Techniques

6.10. Semantic Segmentation

6.10.1. Deep Learning for Semantic Segmentation
6.10.2. Edge Detection
6.10.3. Rule-based Segmentation Methods

Module 7. Processing sequences using RNN (Recurrent Neural Networks) and CNN (Convolutional Neural Networks)

7.1. Recurrent Neurons and Layers

7.1.1. Types of Recurring Neurons
7.1.2. Architecture of a Recurring Layer
7.1.3. Applications of Recurring Layers

7.2. Training of Recurrent Neural Network (RNN)

7.2.1. Backpropagation Through Time (BPTT)
7.2.2. Stochastic Gradient Descending
7.2.3. Regularization in RNN Training

7.3. Evaluation of RNN Models

7.3.1. Evaluation Metrics
7.3.2. Cross Validation
7.3.3. Hyper-Parameters Adjjustment

7.4. RNN Pretrained

7.4.1. Pretrained Network
7.4.2. Learning Transfer
7.4.3. Fine Tuning

7.5. Prognosis of a Time Series

7.5.1. Statistical Models for Forecasts
7.5.2. Methods of Time Series
7.5.3. Neural Network-Based Models

7.6. Interpretation of the Results of Time Series Analysis

7.6.1. Main Component Analysis
7.6.2. Cluster Analysis
7.6.3. Correlation Analysis

7.7. Handling of Long Sequences

7.7.1. Long Short-Term Memory (LSTM)
7.7.2. Gated Recurrent Units (GRU)
7.7.3. 1D Convolutionals

7.8. Partial Sequence Learning

7.8.1. Methods of Deep Learning
7.8.2. Generic Models
7.8.3. Reinforcement Learning

7.9. Practical Application of RNN and CNN

7.9.1. Natural Language Processing
7.9.2. Pattern Recognition
7.9.3. Computer Vision

7.10. Differences in Classical Results

7.10.1. Classic Methods vs. RNN
7.10.2. Classic Methods vs. CNN
7.10.3. Difference in Training Time

Module 8. Natural Language Processing (NLP) with Recursive Natural Networks (RNN) and Attention

8.1. Text Generation Using RNN

8.1.1. Training an RNN for Text Generation
8.1.2. Natural Language Generation with RNN
8.1.3. Text Generation Applications with RNN

8.2. Creating the Training Data Set

8.2.1. Data Preparation for Training an RNN
8.2.2. Storage the Training Data Set
8.2.3. Cleaning and Transformation of Date of Cultural Interest

8.3. Sentiment Analysis

8.3.1. RNN Opinions Classification
8.3.2. Detection of Topics in Comments
8.3.3. Sentiment Analysis with Deep Learning Algorithms

8.4. Training an Encoder-decoder Network for Neural Machine Translation

8.4.1. Training an RNN for Machine Translation
8.4.2. Using an encoder-decoder Network for Machine Translation
8.4.3. Improved Machine Translation Accuracy with RNN

8.5. Attention Mechanism

8.5.1. Application of Care Mechanisms in RNN
8.5.2. Using Attention Mechanisms to Improve Model Accuracy
8.5.3. Advantages of Attention Mechanisms in Neural Networks

8.6. Transformers Models

8.6.1. Transformers Use Model for Natural Language Processing
8.6.2. Transformers Application Model for Vision
8.6.3. Advantages of Transformers Models

8.7. Transformers for Vision

8.7.1. Transformers Use Model for Vision
8.7.2. Data Pre-Processing Imaging
8.7.3. Transformer Training Model for Vision

8.8. Hugging Face Transformers Libraries

8.8.1. Use of Hugging Face Transformers Libraries
8.8.2. Application of Hugging Face Transformers Libraries
8.8.3. Advantage of Hugging Face Transformers Libraries

8.9. Other Transformers.Libraries Comparison

8.9.1. Comparison between Different BookstoresTransformers
8.9.2. Use of other bookstoresTransformers
8.9.3. Advantages of other bookstoresTransformers

8.10. Develop from an Application of NLP Processing with RNN and Attention. Practical Application

8.10.1. Develop from an Application of Natural Language Processing with RNN and Attention
8.10.2. Use of RNN, Service Mechanisms and Transformers Models in the Application
8.10.3. Evaluation of the Practical Application

Module 9. Autoencoders, GANs, and Diffusion Models

9.1. Representation of Efficient Data

9.1.1. Dimensionality Reduction
9.1.2. Deep Learning
9.1.3. Compact Representation

9.2. Implement PCA techniques with an Incomplete Linear Autoencoder

9.2.1. Training Process
9.2.2. Python Implementation
9.2.3. Test Data Use

9.3. Stacked Auto Encoders

9.3.1. Deep Neural Networks
9.3.2. Construction of Coding Architectures
9.3.3. Use of Regularization

9.4. Convolutional Autoencoders

9.4.1. Convolutional Model Design
9.4.2. Convolutional Design Training
9.4.3. Results Evaluation

9.5. Denoising Auto Encoders

9.5.1. Filter Application
9.5.2. Coding Model Design
9.5.3. Use of Regularization Techniques

9.6. Dispersed Auto Encoders

9.6.1. Increase Coding Efficiency
9.6.2. Minimizing the Number of Parameters
9.6.3. Use of Regularization Techniques

9.7. Variational Auto Encoders

9.7.1. Using Variational Optimization
9.7.2. Unsupervised Deep Learning
9.7.3. Deep Latent Representations

9.8. MNIST Image Generation of Fashion

9.8.1. Pattern Recognition
9.8.2. Generation of Images
9.8.3. Training of Deep Neural Networks

9.9. Generative Adversarial Networks and Diffusion Models

9.9.1. Generation of Content from Images
9.9.2. Models of Data Distribution
9.9.3. Use of Adversarial Networks

9.10. Implementation of the Models. Practical Application

9.10.1. Implementation of the Models
9.10.2. Using Real Data
9.10.3. Results Evaluation

Module 10. Reinforcement Learning

10.1. Policy Search and Rewards Optimization

10.1.1. Reward Optimization Algorithms
10.1.2. Policy Search Processes
10.1.3. Reinforcement Learning to Optimize Rewards

10.2. OpenAI

10.2.1. OpenAI Gym Environment
10.2.2. Creation of OpenAI Environments
10.2.3. Reinforcement Learning Algorithms

10.3. Politics of Neural Networks

10.3.1. Convolutional Neural Networks for Policy Search
10.3.2. Politics of Deep Learning
10.3.3. Extension of Neural Network Policies

10.4. Evaluation of Actions: the Problem of the Allocation of Credits

10.4.1. Risk Analysis for Credit Allocation
10.4.2. Loan Profitability Estimation
10.4.3. Credit Evaluation Models Based on Neural Networks

10.5. Policy Gradients

10.5.1. Reinforcement Learning with Policy Gradients
10.5.2. Policy Gradient Optimization
10.5.3. Policy Gradient Algorithms

10.6. Markov Decision Process

10.6.1. Markov Decision Process Optimization
10.6.2. Reinforcement Learning for Markov Decision Processes
10.6.3. Markov Decision Process Models

10.7. Learning and Time Differences and Q-Learning

10.7.1. Using differences in Learning
10.7.2. Using Q-Learning in Learning
10.7.3. Optimization of Q-Learning Parameters

10.8. Implement from Deep Q-Learning and variants of Deep Q-Learning

10.8.1. Building of Deep Neural Networks for Deep Q-Learning
10.8.2. Deep Q- Learning Implementation
10.8.3. Deep Q- Learning Variations

10.9. Reinforment Learning Algorithms

10.9.1. Reinforcement Learning Algorithms
10.9.2. Reward. Learning Algorithms
10.9.3. Punishment Learning Algorithms

10.10. Reinforcement Learning an Environment Design. Practical Application

10.10.1. Reinforcement Learning an Environment Design
10.10.2. Reinforcement Learning an Algorithm Implementation
10.10. 3    Reinforcement Learning an Algorithm Assessment

Specialize in the training, evaluation, and analysis of neural network models thanks to this Master's Degree”