IBM AI Engineering Professional Certificate

This course will teach you how to use Python, a familiar and simple programming language, to machine-learn.

The course covers two main components. First, you will learn about Machine Learning and how it is applied in the real world.
The second gives an overview of Machine Learning topics such as supervised vs unsupervised learning, model evaluation, and Machine Learning algorithms.

This course will enable you to apply Machine Learning in real-life situations, and see how it affects society in unexpected ways.

For the next few months, you can do this by working only a few hours per semaine.

1. You can add new skills to your resume, such as regression, clustering, and classification.
2. You can add projects to your portfolio, such as cancer detection, prediction of economic trends, customer churn prediction and recommendation engines.
3. To demonstrate your competence in machine-learning, you can get a certificate that you can share online or offline through LinkedIn profiles and social media.

If you complete the Coursera course, and earn the Coursera certification, you will be awarded an IBM digital badge.

Are you looking to make a career out of Deep Learning? You have come to the right place. This course will introduce deep learning to you and answer many of the questions people ask nowadays. Learn about deep learning models, and then build your first deep-learning model with Keras.

This course will allow learners to: * describe a neural network, what a deep-learning model is and what the differences between them are. Learn how to understand unsupervised deep learning models like autoencoders or restricted Boltzmann machine. * Demonstrate an understanding of supervised deep-learning models, such as convolutional neural network and recurrent networks. * Create deep learning models and networks with Keras.

Computer Vision is an exciting area of Machine Learning and AI. There are many applications for it, including in self-driving cars and robotics. Augmented reality is another example. This course is easy to understand and will cover the various applications of computer vision across many industries.

This course will teach you how to use Python, Pillow, OpenCV, and OpenCV to perform basic image processing, object classification, and object detection. This course is hands-on and includes several exercises and labs. Labs will include Jupyter Labs combined with Computer Vision Learning Studio (CV Studio), which is a free tool for learning computer vision. CV Studio allows users to upload, train and test their own detection and image classifier models. You will be able to create and deploy your own web-based computer vision app at the end of this course. This course doesn't require any previous Machine Learning or Computer Vision experience. It is however necessary to have some knowledge of Python programming language and high school mathematics.

This course will show you how to create deep learning models with Pytorch. The course will begin with Pytorch's Tensors and Automatic differentiation packages. Each section will then cover different models, starting with Linear Regression and logistic/softmax. Then comes Feedforward deep neural network, which will cover the roles of different activation functions and normalization layers. Convolutional neural networks and Transfer learning will then be covered. Several other Deep learning methods are also covered.

Learning Outcomes

Most of the data in the world are unlabeled or unstructured. Deep neural networks are unable to capture the relevant structure, such as images, sounds, and textual data. These types of data are best suited for deep networks, which can discover hidden structures. This course will teach you how to use TensorFlow library for deep learning on different data types to solve real-world problems.

Learning Outcomes TensorFlow is used for classification, regression, classification, and minimization error functions. Learn about the different types of Deep Architectures such as Convolutional, Recurrent, and Autoencoders. TensorFlow is used to adjust the biases and weights of the Neural Networks being trained.

This capstone will allow learners to apply their deep learning knowledge to solve a real-world problem. To develop and test a deep-learning model, they will use a library that interests them. They will load real data, pre-process it and then build and validate the model. To demonstrate their knowledge and proficiency in Deep Learning, learners will present a project report.

Learning Outcomes