IBM AI Engineering

Describe the various types of Machine Learning algorithms and when to use them. Compare and contrast linear classification methods, including multiclass prediction, support vector machines, and logistic regression. Write Python code that implements various classification techniques, such as K-Nearest neighbors (KNN) and decision trees. Evaluate the results from simple linear, non-linear, and multiple regression on a data set using evaluation metrics.

Looking to start a career in Deep Learning? This course introduces you to the field of deep learning and helps you understand the different deep learning models. You will learn about unsupervised and supervised deep learning models and build your first deep learning model using the Keras library.

Explore the applications of computer vision across different industries, apply image processing and analysis techniques using Python, Pillow, and OpenCV, and create an image classifier using supervised learning techniques.

Demonstrate your comprehension of deep learning algorithms and implement them using PyTorch. Build Deep Neural Networks using PyTorch and apply knowledge of Deep Neural Networks and related machine learning methods.

Understand foundational TensorFlow concepts and its applications in curve fitting, regression, classification, and deep architectures such as Convolutional Networks, Recurrent Networks, and Autoencoders. Apply TensorFlow for backpropagation to tune the weights and biases during training.

In the AI Capstone Project, you will build a deep learning model to solve a real-world problem, execute the process of creating a deep learning pipeline, apply knowledge of deep learning to improve models using real data, and demonstrate your ability to present and communicate outcomes of deep learning projects.