- Course Introduction
- Introduction to Neural Networks
- Basics of Neurons
- Neural Networks with Sklearn
- Neuron in Action
- Neural Networks with SKlearn
- Forward Propagation
- Matrix Representation of Forward Propagation
- Main Types of Deep Neural Network
- (Optional) Introduction to Neural Networks Notebook - Part 1
- (Optional) Introduction to Neural Networks Notebook - Part 2
- Gradient Descent Basics
- Compare Different Gradient Descent Methods
- (Optional) Gradient Descent Notebook - Part 1
- (Optional) Gradient Descent Notebook - Part 2
- (Optional) Gradient Descent Notebook - Part 3
Intermediate
Online
Quick facts
particular | details | |
---|---|---|
Medium of instructions
English
|
Mode of learning
Self study
|
Mode of Delivery
Video and Text Based
|
Course overview
Deep Learning and Reinforcement Learning Certification by Coursera introduces its learners to two of the most sought-after avenues in Machine Learning-Reinforcement Learning and Deep Learning. The latter is abundantly used to power most of the AI applications that are used on a daily basis. Deep Learning and Reinforcement Learning Certification Syllabus exhaustively cover the theory of neural networks that form the basis of Deep Learning as well as modern architectures concerned with Deep Learning.
As an intermediate-level course, it serves as the perfect second step for aspiring data scientists interested in getting hands-on experience with both the domains in Machine Learning to learn at their own pace and earn a certification. Delivered by IBM professionals, the course will focus on Reinforcement Learning once learners have developed a few Deep Learning models. Although Reinforcement Learning has only a few practical applications at present, it is coming up as a promising area of research in AI that is expected to become relevant in the coming future. At the end of the course, data scientists will find them to be well acquainted with the learnings provided in the course. They can easily implement them in their workforce and deliver timely solutions.
The highlights
- Certification and course delivery by IBM
- 31 hours of course duration
- Intermediate-level learning
- Self-paced study pattern
- Free enrollment
Program offerings
- Course readings
- Expert lectures
- Graded assignments
- Quizzes
Course and certificate fees
Deep Learning and Reinforcement Learning Certification Fee structure is as follows-
- Candidates can take up this course for free if they audit for the free course.
Fee Details for Deep Learning and Reinforcement Learning
Particulars | Amount in INR |
Deep Learning and Reinforcement Learning (Audit) | Free |
Deep Learning and Reinforcement Learning - 1 month | Rs.3,243/- |
Deep Learning and Reinforcement Learning - 3 months | Rs.6,486/- |
Deep Learning and Reinforcement Learning - 6 months | Rs.9,729/- |
certificate availability
certificate providing authority
Eligibility criteria
Work experience
Deep Learning and Reinforcement Learning Certification Training prescribe a prior experience with Python development environment programming as a work requisite.
Education
Course participants of the Deep Learning and Reinforcement Learning Certification Programme must have a fundamental understanding of exploratory data analysis, data cleaning, unsupervised learning, calculus, supervised learning, linear algebra, statistics and probability.
Certification qualifying details
All learners who pay for the certification after their free trial can receive Deep Learning and Reinforcement Learning Certification provided they fulfil the additional requirements of obtaining the passing grade in all the graded assignments after verification of their name or ID on Coursera.
What you will learn
Deep Learning and Reinforcement Learning Certification Training prepare data scientists with preliminary knowledge about programming with Python and other basic concepts to enhance their knowledge and incline it towards a machine learning paradigm. After completion, course participants will learn the following-
- Explaining the curse of dimensionality and how it makes clustering difficult with many features
- Clustering points where appropriate, compare the performance of per-cluster models
- Describing and using common clustering and dimensionality-reduction algorithms
- Key concepts in this domain that intervene during model training
- Most common CNN architectures in the current domains
- Understanding metrics relevant for characterising clusters
- Theoretical background of neural networks and characteristics that they share with other machine learning algorithms
- Explaining the kinds of problems suitable for unsupervised learning approaches
- Knowing about Reinforcement Learning through training algorithms by using rewards instead of a method to minimise error
- Describing the use of trained autoencoders for image applications
Who it is for
Deep Learning and Reinforcement Learning Certification Programme is an intermediate course on the two essential concepts of Machine Learning and will this benefit the following groups-
- Data scientists who wish to learn about Reinforcement and Deep Learning.
Admission details
Deep Learning and Reinforcement Learning Certification Online Course can be registered for through the course URL depending upon the type of learning the learner opts for. The registration procedure has been mentioned below-
Step 1: Click on the link- https://www.coursera.org/learn/deep-learning-reinforcement-learning and log in through your account or register on Coursera.
Step 2: Select “Enroll for Free” option.
Step 3: You can choose to begin with your free trial after which you will have to pay for the certification or audit the course for free.
Step 4: On choosing a free trial option, you can begin with the course and pursue for seven days.
Step 5: Auditing the course will allow you to pursue the course for free totally without accessing graded assignments.
The syllabus
Module 1: Introduction to Neural Networks
Videos
Reading
- Summary/Review
Quizzes
- Practice: Introduction to Neural Networks
- Practice: Optimization and Gradient Descent
- End of Module Quiz
App Items
- Neural Networks with Sklearn
- Introduction to Neural Networks Demo (Activity)
- Gradient Descent Demo (Activity)
Module 2: Back Propagation Training and Keras
Videos
- How to Train a Neural Network
- Backpropagation
- (Optional) Backpropagation Notebook - Part 1
- (Optional) Backpropagation Notebook - Part 2
- The Sigmoid Activation Function
- Other Popular Activation Functions
- (Optional) Backpropagation Notebook - Part 3
- Popular Deep Learning Library
- A Typical Keras Workflow
- Implementing an Example Neural Network in Keras
- (Optional) Keras Notebook - Part 1
- (Optional) Keras Notebook - Part 2
- (Optional) Keras Notebook - Part 3
Reading
- Summary/Review
Quizzes
- Practice: Back Propagation, Activation Functions
- Practice: Keras Library
- End of Module Quiz
App Items
- Backpropagation Demo (Activity)
- Keras Demo (Activity)
- Regression with Keras
- (Optional) Loading Images with Keras
Module 3: Neural Network Optimizers
Videos
- Optimizers and Momentum
- Popular Optimizers
- Details of Training Neural Networks
- Data Shuffling
- Transforms
Reading
- Summary/Review
Quizzes
- Practice: Optimizers and Data Shuffling
- End of Module Quiz
App Items
- Optimizers
- Grid Search with Keras
Plugin
- Learning Rate Scheduler Reading
Module 4: Convolutional Neural Networks
Videos
- Categorical Cross Entropy
- Introduction to Convolutional Neural Networks (CNN)
- Images Dataset
- Kernels
- Convolution for Color Images
- Convolutional Settings - Padding and Stride
- Convolutional Settings - Depth and Pooling
- (Optional) Demo CNN Notebook - Part 1
- (Optional) Demo CNN Notebook - Part 2
Reading
- Summary/Review
Quizzes
- Practice: Convolutional Neural Networks
- End of Module Quiz
App Items
- Categorical Cross Entropy
- Images Convolution
- Padding, Pooling, and Stride
- Channels and Flattening
- Training the Network
- Convolutional Neural Networks Demo (Activity)
Module 5: Transfer Learning
Videos
- Introduction to Transfer Learning
- Transfer Learning and Fine Tuning
- (Optional) Transfer Learning Notebook
- Convolutional Neural Network Architectures - LeNet
- Convolutional Neural Network Architectures - AlexNet
- Convolutional Neural Network Architectures - Inception
- Convolutional Neural Network Architectures - ResNet
- Regularization Techniques for Deep Learning
Reading
- Summary/Review
Quizzes
- Practice: Transfer Learning
- Practice: Convolutional Neural Network Architectures
- Practice: Regularization
- End of Module Quiz
App Items
- Transfer Learning Demo (Activity)
- Types of Model APIs in Keras
- Transfer Learning Examples with Existing Architectures
- Regularization Techniques
Plugin
- Regularization Reading
Module 6: Recurrent Neural Networks and Long-Short Term Memory Networks
Videos
- Recurrent Neural Networks (RNNs)
- State and Recurrent Neural Networks
- Details Recurrent Neural Networks
- (Optional) Recurrent Neural Networks Notebook - Part 1
- (Optional) Recurrent Neural Networks Notebook - Part 2
- Long-Short Term Memory (LSTM) Networks
- LSTM Explanation
- Gated Recurrent Unit Gated
- Recurrent Unit Details
Reading
- Summary/Review
Quizzes
- Practice: Recurrent Neural Networks
- Practice: LSTM and GRU
- End of Module Quiz
App Items
- (Optional) Introduction to Sequential Data
- Existing Recurrent Neural Networks
- Word Embeddings
- Recurrent Neural Networks Demo (Activity)
- LSTM and GRU Demo (Activity)
Module 7: Autoencoders
Videos
- Introduction to Autoencoders
- Autoencoders
- (Optional) Autoencoders Notebook - Part 1
- (Optional) Autoencoders Notebook - Part 2
- (Optional) Autoencoders Notebook - Part 3
- (Optional) Autoencoders Notebook - Part 4
- (Optional) Autoencoders Notebook - Part 5
Reading
- Summary/Review
Quizzes
- Practice: Autoencoders
- End of Module Quiz
App Items
- Autoencoders
- Autoencoders Demo (Activity)
Plugin
- Transposed Convolution Reading
Module 8: Generative Models and Applications of Deep
Videos
- What is a Variational Autoencoder
- How Variational Autoencoders Work
- Introduction to GANs
- How GANS Work
- Issues with Training GANS
- Additional Topics in Deep Learning
- Model Agnostic Explainable AI
Reading
- Summary/Review
Quizzes
- Practice: Variational Autoencoders
- Practice: Generative Adversarial Networks
- End of Module Quiz
App Items
- Variational Autoencoder
- GANS Lab 1
- GANS Lab 2
- GPU with Keras
Module 9: Reinforcement Learning
Videos
- Reinforcement Learning (RL)
- (Optional) Reinforcement Learning Notebook - Part 1
- (Optional) Reinforcement Learning Notebook - Part 2
- (Optional) Reinforcement Learning Notebook - Part 3
- (Optional) Reinforcement Learning Notebook - Part 4
Reading
- Summary/Review
Quizzes
- Practice: Reinforcement Learning
- End of Module Quiz
Peer Review
- Final Project
App Items
- Reinforcement Learning Demo (Activity)
Scholarship Details
Scholarship in the form of Coursera financial aid is extended to those individuals whose applications for the same are approved. Interested applicants may apply through the course page by clicking on “Financial Aid available.” Continuing to their application will take them to a declaration after which they need to input their personal information and fill a 150-word application by answering the questions displayed on the screen. Every applicant shall get an email intimation regarding the acceptance and rejection of their application within 15 days.
How it helps
Deep Learning is an important branch of machine learning that boosts the capacity of computers to recognise and process speech and images. Reinforcement learning, on the other hand, allows machines and software agents and to automatically determine their ideal behaviour within a specific context. This maximises its performance. Both these concepts are being used extensively by data scientists to revamp and reshape the software industry.
Deep Learning and Reinforcement Learning Certification Course ensures learners ace in their professional setup by a strong practical experience of these two domains. The course includes practising labs on CNN and RNN which will help candidates encounter and tackle real-world problems through the learning outcomes. The subject matter is quite extensive to enumerate machine learning fundamentals.
Machine Learning has proven to be one of the most sought after skills for vacancies in modern AI applications, a field that has grown manifold throughout the years. Deep Learning and Reinforcement Learning Certification benefits learners with a professional certification from IBM and polishes candidates to pursue a career in Machine Learning. Learners can also pursue other IBM certifications to earn a digital Badge from IBM in recognition of their proficiency in Machine Learning.
Instructors
Mr Mark J Grover
Digital Content Delivery Lead
IBM
Mr Miguel Maldonado
Machine Learning Curriculum Developer
IBM
Mr Joseph Santarcangelo
Data Scientist
IBM
Ph.D
Ms Kopal Garg
Data Scientist
IBM
Other Masters
Ms Xintong Li
Data Scientist
IBM
FAQs
Yes, this can be done by activating calendar sync under the settings on the course dashboard. Any change in deadline will be reflected on the calendar as well.
Quizzes have multiple-choice, short answer and single choice questions. If the options for a question are round, it is a single-choice question. If the options for a quiz are square, it is a multiple-choice question.
Issues with the course material can be brought up in the discussion forum available on the course dashboard.
The most likely reason for this is that the learners might not have completed the course completely. He/she must ensure that all certification qualifying requirements have been met.
Such learners can receive a certification if they purchase the same during or after the course. They will have to perform the additional coursework.
No, some carry a grade while some don't. The former contribute towards the certification while the latter is just for practice.
Learners who have paid for the professional certification but have not claimed a refund within the deadline cannot unenroll from this course.
The deadline for completing assignments will be displayed on the course dashboard once the assignment activates or is unlocked.
They can be accessed offline only if they are downloaded, which can be done by selecting "lecture video" under downloads section on the course dashboard.
Learners need to have the latest versions of any of the given browsers-
- Google Chrome (recommended)
- Safari
- Firefox
- Internet Explorer 11
- Microsoft Edge
Articles
Popular Articles
Latest Articles
Similar Courses
Intermediate Intel Distribution of OpenVino Toolki...
Intel via Coursera
Introduction to Neural Networks and Deep Learning
Great Learning
Introduction to TensorFlow Lite
TensorFlow via Udacity
Neural Networks and Deep Learning
Deep learning via Coursera
Introduction to Deep Learning with PyTorch
Facebook via Udacity
Deep Learning Fundamentals with Keras
IBM via Edx
Specialized Models Time Series and Survival Analys...
IBM via Coursera
Using GPUs to Scale and Speed-up Deep Learning
IBM via Edx
Deep Learning Essentials
University of Montreal, Montreal via Edx
Courses of your interest
Salesforce Administrator and App Builder
SkillUp Online via Simplilearn
Introduction to Medical Software
Yale University, New Haven via Coursera
Google Cloud Architect Program
Google Cloud via SkillUp Online
Google Cloud Architect Program
Google via SkillUp Online
Information Security Design and Development
Coventry University, Coventry via Futurelearn
Ethics Laws and Implementing an AI Solution on Mic...
CloudSwyft Global Systems, Inc via Futurelearn
Network Security and Defence
Coventry University, Coventry via Futurelearn
Cyber Security Foundations Start Building Your Car...
EC-Council via Futurelearn
Applied Data Analysis
CloudSwyft Global Systems, Inc via Futurelearn
More Courses by IBM
AI Applications With Watson
IBM via Edx
Python for Data Science Project
IBM via Edx
Site Reliability Engineering Capstone
IBM via Edx
Blockchain Framework and Platforms
IBM via Edx
Introduction to System Programming on IBM Z
IBM via Edx
Smarter Chatbots with Node RED and Watson AI
IBM via Edx
Application Development using Microservices and Se...
IBM via Coursera
IBM Data Topology
IBM via Coursera