Deep Learning Architectures for Defense and Security Training
Course Authors
Deep Learning Architectures for Defense and Security Training Hands-on (Online, Onsite, and Classroom Live)
| Commitment | 3 Days, 7-8 hours a day. |
| Language | English |
| User Ratings | Average User Rating 4.8 See what learners said |
| Price | REQUEST |
| Delivery Options | Instructor-Led Onsite, Online, and Classroom Live |
COURSE OVERVIEW
This 3-day Deep Learning Architectures for Defense and Security Training course provides a broad introduction to classical neural networks (NN) and its current evolution to deep learning (DL) technology. This Deep Learning Architectures for Defense and Security course introduces the well-known deep learning architectures and their applications in defense and security for object detection, identification, verification, action recognition, scene understanding, and biometrics using a single modality or multimodality sensor information. This Deep Learning Architectures for Defense and Security course will describe the history of neural networks and their progress to current deep learning technology. It covers several DL architectures such the classical multi-layer feed-forward neural networks, convolutional neural networks (CNN), generative adversarial networks (GAN), restricted Boltzmann machines (RBM), auto-encoders and recurrent neural networks such as long-term short memory (LSTM).
The use of deep learning architectures for feature extraction and classification will be described and demonstrated. Examples of popular CNN-based architectures such as AlexNet, VGGNet, GooGleNet (inception modules), ResNet, DeepFace, Highway Networks, and FractalNet and their applications to defense and security will be discussed. Advanced architectures such as Siamese deep networks, coupled neural networks, conditional adversarial generative networks, a fusion of multiple CNNs, and their applications to object verification and classification will also be covered. The Deep Learning Architectures for Defense and Security Training course is for scientists, engineers, technicians, or managers who wish to learn more about deep learning architectures and their applications in defense and security.
WHAT'S INCLUDED?
- 3 days of Deep Learning Architectures for Defense and Security Training with an expert instructor
- Deep Learning Architectures for Defense and Security Course Guide
- Certificate of Completion
- 100% Satisfaction Guarantee
RESOURCES
- Deep Learning Architectures for Defense and Security Training – https://www.wiley.com/
- Deep Learning Architectures for Defense and Security – https://www.packtpub.com/
- Deep Learning Architectures for Defense and Security – https://store.logicaloperations.com/
- Deep Learning Architectures for Defense and Security – https://us.artechhouse.com/
- Deep Learning Architectures for Defense and Security – https://www.amazon.com/
RELATED COURSES
- Cloud Security Fundamentals Training
- Computer Forensics Training
- Certified Powershell Hacker (CPSH) Training
- Cybersecurity Foundations Training
- Cyber Threats Detection and Mitigation Training
- Cyber Threats Hunting (CCTHP) Training
- Cyber Threat Intelligence Analysis Training
- Cybersecurity Investigations and Network Forensics Analysis
ADDITIONAL INFORMATION
COURSE OBJECTIVES
Upon completing this Deep Learning Architectures for Defense and Security Training course, learners will be able to meet these objectives:
- Fundamental concepts of neural networks and deep learning.
- Differences between neural network and current deep learning architectures.
- Stochastic gradient descent algorithm to train deep learning networks
- The popular CNN-based architectures (i.e., LeNet, AlexNet, VGGNet, GooGleNet, ResNet).
- Relative merits of various deep learning architectures, MLP, CNN, GAN, RBM, and LSTM.
- Auto-encoders for feature extraction. Generative adversarial networks for object synthesis.
- Deep learning framework for an object, pedestrian detection, face, iris, and fingerprint identification.
- Siamese and coupled deep learning architectures for cross-modal object verification & identification.
- Deep learning architectures for multi-view face identification and multimodal biometrics applications.
CUSTOMIZE IT
- We can adapt this Deep Learning Architectures for Defense and Security Training course to your group’s background and work requirements at little to no added cost.
- If you are familiar with some aspects of this Deep Learning Architectures for Defense and Security course, we can omit or shorten their discussion.
- We can adjust the emphasis placed on the various topics or build the Deep Learning Architectures for Defense and Security around the mix of technologies of interest to you (including technologies other than those included in this outline).
- If your background is nontechnical, we can exclude the more technical topics, include the topics that may be of special interest to you (e.g., as a manager or policy-maker), and present the Deep Learning Architectures for Defense and Security course in a manner understandable to lay audiences.
AUDIENCE/TARGET GROUP
The target audience for this Deep Learning Architectures for Defense and Security Training course:
- All
CLASS PREREQUISITES
The knowledge and skills that a learner must have before attending this Deep Learning Architectures for Defense and Security Training course are:
- Understanding of fundamental information security concepts
- Basic knowledge of Linux and Windows command line
COURSE SYLLABUS
- History of Neural Networks. Origin of the artificial neural networks (ANN) and its relationship with artificial intelligence & expert systems. Artificial neuron models vs biological neurons. Characteristics of receptive fields of neurons in the visual cortex. Binary and continues perceptrons.
- Multi-layer Perceptrons. Concept of layering, basics of gradient descent, and backpropagation learning algorithm for network training.
- Activation functions. Non-linearity functions in neural networks, Hard limiting, Sigmoid, Tanh, and ReLU functions.
- Overfitting and Generalization. The concept of overfitting and generalization in deep learning, sparsity-based regularization, L1 sparsity, L2 sparsity, and groups sparsity, and the concept of dropout as regularization.
- Auto-encoders. Denoising autoencoders, hetero-associative auto-encoders, sparse autoencoders, convolutional autoencoders, learning manifold, and dimensionality reduction. Deep Learning Architectures for Defense and Security Training
- Restricted Boltzmann Machines. The idea behind the classical RBM and deep belief nets.
- Convolutional Neural Network architectures. Concept of convolution neural network architectures and the functions of its layers. Use of different kernel sizes, average pooling, max pooling, and concept of using overlapping and non-overlapping strides.
- Modern Convolutional Neural Network architectures. LeNet, AlexNet, VGGNet, GoogleNet, ResNet, DeepFace, Highway Networks, and FractalNet.
- Generative Adversarial Networks (GAN). Concept of GAN and conditional GAN for cross-modality synthesis, image restoration, and distortion removal.
- Coupled & Siamese Deep Neural Networks. Cross-modal face and object classification, image search and retrieval, Cross-modal deep hashing, Siamese networks for distance metric learning.
- Multisensory Fusion architectures. Deep fusion architectures, deep learning architectures for multimodality, and Multiview.
- Applications of Deep Neural Networks. CNN-based object recognition and detection, deep automatic target recognition, deep biometrics (face, iris, fingerprint, voice), cross-spectral classification, scene-to-text generation, sketch-to-photo synthesis, and object pedestrian detection from surveillance cameras or moving platforms.
