Fundamental Artificial Intelligence
Duration
Exam Details
- Exam Code: AI90.01: Artificial Intelligence Specialist
- Duration: 110 Minutes
- A passing grade on Exam AI90.01 is required to is required to achieve the Artificial Intelligence Specialist Certification.
- Availability: Pearson VUE Testing Centers Worldwide, Pearson VUE Online Proctoring, On-Site Proctoring.
Price
This course provides essential coverage of artificial intelligence and neural networks in easy-to-understand, plain English. The course provides concrete coverage of the primary parts of AI, including learning approaches, functional areas that AI systems are used for and a thorough introduction to neural networks, how they exist, how they work and how they can be used to process information.
The course establishes the five primary business requirements AI systems and neural networks are used for, and then maps individual practices, learning approaches, functionalities and neural network types to these business categories and to each other, so that there is a clear understanding of the purpose and role of each topic covered. The course further establishes a step-by-step process for assembling an AI system, thereby illustrating how and when different practices and components of AI systems with neural networks need to be defined and applied. Finally, the course provides a set of key principles and best practices for AI projects.
Key Outcomes:
Students will be able to know:
- AI Business and Technology Drivers, Benefits and Challenges, Types
- Common AI Learning Approaches and Algorithms
- Robotics, Natural Language Processing (NLP)
- Loss, Hyperparameters, Learning Rate, Bias, Epoch
- Support Vector Machine, Kohonen Network, Hopfield Network
- etc
Objectives
- AI Business and Technology Drivers
- AI Benefits and Challenges
- Business Problem Categories Addressed by AI
- AI Types (Narrow, General, Symbolic, Non-Symbolic, etc.)
- Common AI Learning Approaches and Algorithms
- Supervised Learning, Unsupervised Learning, Continuous Learning
- Heuristic Learning, Semi-Supervised Learning, Reinforcement Learning
- Common AI Functional Designsl
- Computer Vision, Pattern Recognition
- Robotics, Natural Language Processing (NLP)
- Speech Recognition, Natural Language Understanding (NLU)
- Frictionless Integration, Fault Tolerance Model Integration
- Neural Networks, Neurons, Layers, Links, Weights
- Understanding AI Models and Training Models and Neural Networks
- Understanding how Models and Neural Networks Exist
- Loss, Hyperparameters, Learning Rate, Bias, Epoch
- Activation Functions (Sigmoid, Tanh, ReLU, Leaky RelU, Softmax, Softplus)
- Neuron Cell Types (Input, Backfed, Noisy, Hidden, Probabilistic, Spiking, Recurrent, Memory, Kernel, nvolution, Pool, Output, Match Input, etc.)
- Fundamental and Specialized Neural Network Architectures
- Perceptron, Feedforward, Deep Feedforward, AutoEncoder, Recurrent, Long/Short Term Memory
- Deep Convolutional Network, Extreme Learning Machine, Deep Residual Network
- Support Vector Machine, Kohonen Network, Hopfield Network
- Generative Adversarial Network, Liquid State Machine
- How to Build an AI System (Step-by-Step)
Contact
- Nurman (+62 857-2375-3840)
- Irna (+62 822-1664-7749)
- Puji (+62 813-2424-2115)