Modern Artificial Intelligence with Zero Coding
Modern Artificial Intelligence with Zero Coding
Build 5 Practical Projects & Harness the Power of AI to solve practical, real-world business problems with Zero Coding!
Created by Dr. Ryan Ahmed, Ph.D., MBA, Ligency Team, Mitchell Bouchard | 9.5 hours on-demand video course
Artificial intelligence is one of the top tech fields to be in right now! AI will change our lives in the same way electricity did 100 years ago. AI is widely adopted in Finance, banking, healthcare, transportation, and technology. The field is exploding with opportunities and career prospects. This course solves a key problem which is making AI available to anyone with no coding background or computer science degree. The purpose of this course is to provide you with knowledge of key aspects of modern AI without any intimidating mathematics and in a practical, easy, and fun way. The course provides students with practical hands-on experience using real-world datasets.
What you’ll learn
- Build, train and deploy AI models to detect people emotions using Google Teachable Machine
- Explain the difference between learning rate, epochs, batch size, accuracy and loss.
- Predict Insurance Premium using Customer Features such as age, smoking habit and geo-location using AWS AI AutoPilot
- Build, train and deploy advanced AI to detect cardiovascular disease using DataRobot AI
- Leverage the power of AI to recognize food types using DataRobot AI
- Develop an AI model to detect and classify chest disease using X-Ray chest data using Google Teachable Machines
- Evaluate trained AI models using various KPIs such as confusion matrix, classification accuracy, and error rate
- List the various advantages of transfer learning and know when to properly apply the technique to speed up training process
- Understand the theory and intuition behind residual networks, a state-of-the-art deep neural networks that are widely adopted in business, and healthcare
- Learn how to train multiple AI models based on XG-Boost, Artificial Neural Networks, Random
- Forest Classifiers and compare their performance in DataRobot
- Understand the impact of classifier threshold on False Positive Rate (Fallout) and True Positive Rate (Sensitivity)
- Learn how to use SageMaker Studio AutoML tool to build, train and deploy AI/Ml models which requires almost zero coding experience
- Differentiate between various regression models KPIs such as R2 or coefficient of determination, Mean absolute error, Mean Squared error, and Root Mean Squared Error
- Build, train and deploy XGBoost-based algorithm to perform regression tasks using AWS SageMaker Autopilot
Recommended Course
