This course covers the fundamentals of deep learning and its modern applications, including large language models and multimodal systems. It starts with an introduction to deep learning concepts, history, and necessary background. Students will learn the basics of neural networks through programming exercises, including how artificial neurons function, how networks are trained with algorithms such as backpropagation, and how to address issues like vanishing gradients and overfitting. The course then covers advanced topics such as convolutional neural networks for image classification, sequential models for language tasks, and building AI systems for translation, image captioning, and multitask learning. Students will gain practical experience using frameworks like TensorFlow and PyTorch. The course is suitable for those seeking to expand their knowledge and gain skills needed to build and deploy deep learning models.
Learning Deep Learning: Unit 1
This course is part of Learning Deep Learning Specialization
Instructor: Pearson
Access provided by Defense Acquisition University
Recommended experience
What you'll learn
Grasp the core concepts and history of deep learning, including neural network fundamentals and training algorithms.
Develop hands-on skills in building, training, and evaluating neural networks using TensorFlow and PyTorch.
Apply advanced techniques to solve real-world problems in image classification, language processing, and multimodal AI.
Understand practical considerations and ethical aspects of deploying deep learning in real-world applications.
Skills you'll gain
Details to know
Add to your LinkedIn profile
3 assignments
August 2025
See how employees at top companies are mastering in-demand skills
Build your subject-matter expertise
- Learn new concepts from industry experts
- Gain a foundational understanding of a subject or tool
- Develop job-relevant skills with hands-on projects
- Earn a shareable career certificate
There is 1 module in this course
This module provides a comprehensive introduction to deep learning, starting with its history and foundational concepts. It covers the basics of neural networks, including perceptrons, learning algorithms, and the backpropagation algorithm, with hands-on programming examples. The module progresses to advanced topics such as multiclass classification, deep learning frameworks (TensorFlow and PyTorch), and challenges like vanishing gradients. Learners will also explore techniques for improving network performance, including activation functions, regularization, and handling different problem types, all reinforced through practical coding exercises.
What's included
33 videos3 assignments
Earn a career certificate
Add this credential to your LinkedIn profile, resume, or CV. Share it on social media and in your performance review.
Why people choose Coursera for their career
