Deep Learning

Please Note: Learners who successfully complete this IBM course can earn a skill badge —a detailed, verifiable and digital credential that profiles the knowledge and skills you’ve acquired in this course. Enroll to learn more, complete the course and claim your badge!

Looking to kickstart a career in deep learning? Look no further. This course will introduce you to the field of deep learning and teach you the fundamentals. You will learn about some of the exciting applications of deep learning, the basics fo neural networks, different deep learning models, and how to build your first deep learning model using the easy yet powerful library Keras.

This course will presentsimplified explanations to some oftoday's hottest topics in data science, including:

• What is deep learning?
• How do neural networks learn and what are activation functions?
• What are deep learning libraries and how do they compare to one another?
• What are supervised and unsupervised deep learning models?
• How to use Keras to build, train, and test deep learning models?

The demand fordeep learning skills-- and the job salaries of deep learning practitioners -- arecontinuing to grow, as AI becomes more pervasive in our societies. This course will help you build the knowledge you need to future-proofyour career.

Please Note: Learners who successfully complete this IBM course can earn a skill badge — a detailed, verifiable and digital credential that profiles the knowledge and skills you’ve acquired in this course. Enroll to learn more, complete the course and claim your badge!

NOTE: In order to be successful in completing this course, please ensure you are familiar with PyTorch Basics and have practical knowledge to apply it to Machine Learning. If you do not have this pre-requiste knowledge, it is highly recommended you complete the PyTorch Basics for Machine Learning course prior to starting this course.

This course is the second part of a two-part course on how to develop Deep Learning models using Pytorch.

In the first course, you learned the basics of PyTorch; in this course, you will learn how to build deep neural networks in PyTorch. Also, you will learn how to train these models using state of the art methods. You will first review multiclass classification, learning how to build and train a multiclass linear classifier in PyTorch. This will be followed by an in-depth introduction on how to construct Feed-forward neural networks in PyTorch, learning how to train these models, how to adjust hyperparameters such as activation functions and the number of neurons.

You will then learn how to build and train deep neural networks—learning how to apply methods such as dropout, initialization, different types of optimizers and batch normalization. We will then focus on Convolutional Neural Networks, training your model on a GPU and Transfer Learning (pre-trained models). You will finally learn about dimensionality reduction and autoencoders. Including principal component analysis, data whitening, shallow autoencoders, deep autoencoders, transfer learning with autoencoders, and autoencoder applications.

Finally, you will test your skills in a final project.

Please Note: Learners who successfully complete this IBM course can earn a skill badge — a detailed, verifiable and digital credential that profiles the knowledge and skills you’ve acquired in this course. Enroll to learn more, complete the course and claim your badge!

Traditional neural networks rely on shallow nets, composed of one input, one hidden layer and one output layer. Deep-learning networks are distinguished from these ordinary neural networks having more hidden layers, or so-called more depth. These kind of nets are capable of discovering hidden structures withinunlabeled and unstructured data (i.e. images, sound, and text), which consitutes the vast majority of data in the world.

TensorFlow is one of the best libraries to implement deep learning. TensorFlow is a software library for numerical computation of mathematical expressional, using data flow graphs. Nodes in the graph represent mathematical operations, while the edges represent the multidimensional data arrays (tensors) that flow between them. It was created by Google and tailored for Machine Learning. In fact, it is being widely used to develop solutions with Deep Learning.

In this TensorFlow course, you will learn the basic concepts of TensorFlow, the main functions, operations and the execution pipeline. Starting with a simple “Hello Word” example, throughout the course you will be able to see how TensorFlow can be used in curve fitting, regression, classification and minimization of error functions.

This concept is then explored in the Deep Learning world. You will learn how to apply TensorFlow for backpropagation to tune the weights and biases while the Neural Networks are being trained. Finally, the course covers different types of Deep Architectures, such as Convolutional Networks, Recurrent Networks and Autoencoders.

Please Note: Learners who successfully complete this IBM course can earn a skill badge — a detailed, verifiable and digital credential that profiles the knowledge and skills you’ve acquired in this course. Enroll to learn more, complete the course and claim your badge!

Training acomplex deep learning model with a very large data set can take hours, days and occasionally weeks to train. So, what is the solution? Accelerated hardware.

You can use accelerated hardware such as Google’s Tensor Processing Unit (TPU) or Nvidia GPU to accelerate your convolutional neural network computations time on the Cloud. These chips are specifically designed to support the training of neural networks, as well as the use of trained networks (inference). Accelerated hardware has recently been proven to significantly reduce training time.

But the problem is that your data might be sensitiveand you may not feel comfortable uploading it on a public cloud, preferring to analyze it on-premise. In this case, you need to use an in-house system with GPU support. One solution is to use IBM’s Power Systems with Nvidia GPU and Power AI. The Power AI platform supports popular machine learning libraries and dependencies including Tensorflow, Caffe, Torch, and Theano.

In this course, you'll understand what GPU-based accelerated hardware is and how it can benefit your deep learning scaling needs. You'll also deploy deep learning networks on GPU accelerated hardware for several problems, including the classification of images and videos.