Deep Learning
Learn how to use neural networks to solve problems with Deep Learning certification by Carnegie Mellon University’s School of Computer Science.
Online
10 Weeks
2,500 USD Quick Facts
| Medium Of Instructions | Mode Of Learning | Mode Of Delivery |
|---|---|---|
| English | Self Study, Virtual Classroom | Video and Text Based |
Course Overview
Deep learning is a powerful technology that is being used to solve problems in many different areas. Deep Learning is a 10-week-long online certification course which is brought to you by Carnegie Mellon University’s School of Computer Science Executive and Professional Education along with the online education provider Emeritus. This online course will teach you the basics of deep learning and how to apply it to real-world problems. With the help of this course, you will be able to understand how neural networks operate, identify the right architecture for your needs, and generate and refine deep learning models.
The Deep Learning certification by Carnegie Mellon University’s School of Computer Science will teach you the basics of deep learning and how to apply it to real-world problems. You will learn about different neural network architectures, including CNNs and RNNs. You will also learn about the concepts necessary to solve time-based problems.
Also Read: Online Deep Learning with Python Certification Courses
The Highlights
- 10 weeks online course
- Offered by Carnegie Mellon University
- Programming Assignments
- Capstone project
- Peer Discussion
Programme Offerings
- Certificate of completion
- Online Classes
- Lecture videos
- Knowledge checks
- Flexibility
Courses and Certificate Fees
| Certificate Availability | Certificate Providing Authority |
|---|---|
| yes | CMU Pittsburgh |
The fees for the Deep Learning course is :
| Fees components | Amount |
| Course fees | $ 2,000 |
Eligibility Criteria
Certification Qualifying Details
Upon successful completion of this course, you will receive the Deep Learning certification by Carnegie Mellon University’s School of Computer Science.
What you will learn
After completing the Deep Learning certification syllabus, you will be able to understand how neural networks operate and identify the right architecture for your needs. Also, you will be able to understand the concept of neural network architectures.
Upon completion of the Deep Learning training, you will learn how to generate and refine deep learning models and solve prediction and identification problems. You will also learn the necessary concepts for solving time-based problems.
Who it is for
The Deep Learning online course is designed for participants who want to gain a deeper understanding of neural networks and develop the skills to solve complex problems using deep learning. This course is mainly useful for
Admission Details
Candidates can follow these instructions to join the Deep Learning classes:
Step 1: Go through the URL below: https://execonline.cs.cmu.edu/deep-learning
Step 2: Fill out the required details
Step 3: Download the brochure
Step 4: Go through the course page and click on ‘Apply Now’
Step 5: Fill out the application form online and pay the course fee
Application Details
To enrol in the Deep Learning certification course, you must complete the online application form on the official provider website.
The Syllabus
- Describe significant impacts and successful use cases of neural networks in contemporary society
- Describe the origins of modern connectionist neural networks with respect to early models of human cognition
- Describe the structure and function of a perceptron
- Describe a multilayer perceptron as a function with tunable parameters
- Characterize learning as the process of estimating model parameters to minimize error between the network function and the target function
- Define a gradient as a vector of partial derivatives
- Describe the relationship of the learning rate and the ability of gradient descent to converge to a global minimum of a function
- Describe incremental updates (i.e., stochastic gradient descent) to learn network parameters
- Explain the necessary conditions for stochastic gradient descent to converge
- Describe the need for shift-invariant pattern detection
- Describe the process of shift-invariant pattern detection using a scanning neural network
- Explain the training of neural networks with shared parameters
- Summarize the backpropagation process through flat, convolutional, and pooling layers of a convolutional neural network
- Explain how to compute derivatives for the affine map in convolutional layers of a convolutional neural network through backpropagation
- Explain the dependency paths between individual elements of an activation map and the loss
- Describe the types of problems that require recurrence in neural networks
- Explain the pictorial representation of recurrent neural networks used in this program
- Explain why recurrent connections are needed to refer to historical trends and patterns
- Describe the architecture and training process for a time-synchronous recurrent neural network
- Describe the greedy approach to decoding the output of an order-synchronous but time-asynchronous recurrent network
- Identify the role of alignment in terms of computing divergence between input and output for an order-synchronous but time-asynchronous recurrent network
- Explain how to compute embeddings of words from one-hot encodings, using language prediction with neural networks
- Describe the architecture of a recurrent neural network used for language prediction
- Describe the synchrony problem of sequence-to-sequence models
- Describe the problem of overlapping classes
- Explain the relationship of the logistic regression model and a perceptron with a sigmoid activation function
- Describe how the maximum likelihood estimate is used to learn the parameters of a logistic regression model
- Describe the architecture and purpose of a multi-head self attention block in the context of encoders
- Summarize steps used to train the encoder and decoder of a variational autoencoder
- Contrast properties of variational autoencoders with generative adversarial networks
CMU Pittsburgh Frequently Asked Questions (FAQ's)
This course requires basic programming knowledge (Python or R), math skills (linear algebra and calculus), and an interest in machine learning and artificial intelligence.
The course is delivered online and consists of video lectures, hands-on exercises, and programming assignments.
The course can be completed in 10 weeks which requires 10-15 hours of learning per week.
To earn the certification, you must complete all ten modules in this online course.
Professionals like software developers, data scientists, and AI developers can benefit from this course.