Deep Learning with IBM
Offered By: IBM via edX
Course Description
Overview
AI is revolutionizing the way we live, work and communicate. At the heart of AI is Deep Learning. Once a domain of researchers and PhDs only, Deep Learning has now gone mainstream thanks to its practical applications and availability in terms of consumable technology and affordable hardware.
The demand for Data Scientists and Deep Learning professionals is booming, far exceeding the supply of personnel skilled in this field. The industry is clearly embracing AI, embedding it within its fabric. The demand for Deep Learning skills by employers -- and the job salaries of Deep Learning practitioners -- are only bound to increase over time, as AI becomes more pervasive in society. Deep Learning is a future-proof career.
Within this series of courses, you’ll be introduced to concepts and applications in Deep Learning, including various kinds of Neural Networks for supervised and unsupervised learning. You’ll then delve deeper and apply Deep Learning by building models and algorithms using libraries like Keras, PyTorch, and Tensorflow. You’ll also master Deep Learning at scale by leveraging GPU accelerated hardware for image and video processing, as well as object recognition in Computer Vision.
Throughout this program you will practice your Deep Learning skills through a series of hands-on labs, assignments, and projects inspired by real world problems and data sets from the industry. You’ll also complete the program by preparing a Deep Learning capstone project that will showcase your applied skills to prospective employers.
This program is intended to prepare learners and equip them with skills required to become successful AI practitioners and start a career in applied Deep Learning.
Syllabus
Course 1: Deep Learning Fundamentals with Keras
New to deep learning? Start with this course, that will not only introduce you to the field of deep learning but give you the opportunity to build your first deep learning model using thepopular Keras library.
Course 2: PyTorch Basics for Machine Learning
This course is the first part in a two part course and will teach you the fundamentals of PyTorch. In this course you will implement classic machine learning algorithms, focusing on how PyTorch creates and optimizes models. You will quickly iterate through different aspects of PyTorch giving you strong foundations and all the prerequisites you need before you build deep learning models.
Course 3: Deep Learning with Python and PyTorch
This course is the second part of a two-part course on how to develop Deep Learning models using Pytorch.
Course 4: Deep Learning with Tensorflow
Much of theworld's data is unstructured. Think images, sound, and textual data. Learn how to apply Deep Learning with TensorFlow to this type of data to solve real-world problems.
Course 5: Using GPUs to Scale and Speed-up Deep Learning
Training complex deep learning models with large datasets takes along time. In this course, you will learn how to use accelerated GPU hardware to overcome the scalability problem in deep learning.
Course 6: Applied Deep Learning Capstone Project
In this capstone project, you'll use either Keras or PyTorch to develop, train, and test a Deep Learning model. Load and preprocess data for a real problem, build the model and then validate it.
Courses
-
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.
-
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!
In this capstone project, you'lluse a Deep Learning library ofyour choice to develop, train, and test a Deep Learning model.Loadand preprocess data for a real problem, build the model and then validate it.
Finally, you will present a project report to demonstrate the validity of yourmodel andyour proficiency in the field of 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!
This course is the first part in a two part course and will teach you the fundamentals of Pytorch while providing the necessary prerequisites you need before you build deep learning models.
We will start off with PyTorch's tensors in one dimension and two dimensions , you will learn the tensor types an operations, PyTorchs Automatic Differentiation package and integration with Pandas and Numpy. This is followed by an in-depth overview of the dataset object and transformations; this is the first step in building Pipelines in PyTorch.
In module two we will learn how to train a linear regression model. You will review the fundamentals of training your model including concepts such as loss, cost and gradient descent. You will learn the fundamentals of PyTorch including how to make a prediction using PyTorch's linear class and custom modules. Then determine loss and cost with PyTorch. Finally you will implement gradient descent via first principles.
In module three you will train a linear regression model via PyTorch's build in functionality, developing an understanding of the key components of PyTorch. This will include how to effectively train PyTorch's custom modules using the optimizer object, allowing you an effective way to train any model. We will introduce the data loader allowing you more flexibility when working with massive datasets . You will learn to save your model and training in applications such as cross validation for hyperparameter selection, early stopping and checkpoints.
In module three you will learn how to extend your model to multiple input and output dimensions in applications such as multiple linear regression and multiple output linear regression. You will learn the fundamentals of the linear object, including how it interacts with data with different dimensions and number of samples. Finally you will learn how to train these models in PyTorch.
In module four you will review linear classifiers, logistic regression and the issue of using different loss functions. You will learn how to implement logistic regression in PyTorch several ways, including using custom modules and using the sequential method. You will test your skills in a final project.
Taught by
Joseph Santarcangelo, Alex Aklson and SAEED AGHABOZORGI
Tags
Related Courses
Google Certified Professional Data EngineerA Cloud Guru TensorFlow Developer Certificate Exam Prep
A Cloud Guru Activity Recognition using Python, Tensorflow and Keras
Coursera Project Network via Coursera Post Graduate Certificate in Advanced Machine Learning & AI
Indian Institute of Technology Roorkee via Coursera Advanced Computer Vision with TensorFlow
DeepLearning.AI via Coursera