Deep Learning & Modern AI Architectures
Keep adding new skills with 10,000+ programs for $239 (usually $399). Save now.
Deep Learning & Modern AI Architectures
This course is part of AI Engineering Masterclass: From Zero to AI Hero Specialization
Included with
Ask Coursera
Recommended experience
Recommended experience
What you'll learn
Build and train neural networks using TensorFlow, Keras, and PyTorch.
Implement and optimize CNN architectures for image classification tasks.
Apply RNNs and LSTMs for sequence modeling tasks such as text generation and sentiment analysis.
Utilize Transformer models and pre-trained models for advanced NLP applications.
Skills you'll gain
- Recurrent Neural Networks (RNNs)
- Model Optimization
- Natural Language Processing
- Machine Learning Methods
- Image Analysis
- Model Training
- Fine-tuning
- Artificial Intelligence and Machine Learning (AI/ML)
- Applied Machine Learning
- Transfer Learning
- Deep Learning
- Artificial Neural Networks
- Convolutional Neural Networks
Details to know
February 2026
7 assignments
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 are 5 modules in this course
This course features Coursera Coach!
A smarter way to learn with interactive, real-time conversations that help you test your knowledge, challenge assumptions, and deepen your understanding as you progress through the course. This course will introduce you to the cutting-edge techniques and architectures in deep learning and AI. You will start by mastering the fundamentals of neural networks and deep learning, including key concepts like forward propagation, backpropagation, and gradient descent. From there, you will advance to Convolutional Neural Networks (CNNs) for image classification tasks and Recurrent Neural Networks (RNNs) for sequence modeling tasks such as time series prediction and text generation. As you progress, you will explore the revolutionary Transformer architecture, its self-attention mechanism, and its application in Natural Language Processing (NLP) tasks like text summarization and translation. This course will also cover transfer learning, allowing you to fine-tune pre-trained models for your own tasks, saving time and improving model accuracy. With hands-on projects using frameworks like TensorFlow, Keras, and PyTorch, you will apply your skills to real-world challenges. The course is designed for intermediate learners with prior knowledge of machine learning or neural networks. If you're a machine learning enthusiast or aspiring AI engineer looking to deepen your understanding of deep learning models and their real-world applications, this course will take your skills to the next level. By the end of the course, you will be able to design and implement advanced deep learning models, including CNNs, RNNs, and Transformers, and use transfer learning techniques to fine-tune models for specific tasks such as image classification, text generation, and more.
In this module, we will introduce you to neural networks and deep learning, exploring their foundational concepts and optimization techniques. You’ll learn how to build models with popular frameworks like TensorFlow, Keras, and PyTorch, and apply your skills to a hands-on image classification project using the CIFAR-10 dataset.
What's included
8 videos2 readings1 assignment
8 videos•Total 137 minutes
- Introduction to Week 9 Neural Networks and Deep Learning Fundamentals•1 minute
- Day 1: Introduction to Deep Learning and Neural Networks•16 minutes
- Day 2: Forward Propagation and Activation Functions•15 minutes
- Day 3: Loss Functions and Backpropagation•16 minutes
- Day 4: Gradient Descent and Optimization Techniques•22 minutes
- Day 5: Building Neural Networks with TensorFlow and Keras•19 minutes
- Day 6: Building Neural Networks with PyTorch•26 minutes
- Day 7: Neural Network Project – Image Classification on CIFAR-10•22 minutes
2 readings•Total 20 minutes
- Introduction to the Course 'Deep Learning & Modern AI Architectures'•10 minutes
- Full Specialization Resources•10 minutes
1 assignment•Total 15 minutes
- Week 9: Neural Networks and Deep Learning Fundamentals - Assessment•15 minutes
In this module, we will dive deep into CNNs, focusing on their unique architecture designed for image classification tasks. You will learn how to implement CNNs using Keras, TensorFlow, and PyTorch, while enhancing model performance through regularization and data augmentation techniques. Finally, apply your knowledge in an image classification project.
What's included
8 videos1 assignment
8 videos•Total 161 minutes
- Introduction to Week 10 Convolutional Neural Networks (CNNs)•1 minute
- Day 1: Introduction to Convolutional Neural Networks•26 minutes
- Day 2: Convolutional Layers and Filters•24 minutes
- Day 3: Pooling Layers and Dimensionality Reduction•24 minutes
- Day 4: Building CNN Architectures with Keras and TensorFlow•18 minutes
- Day 5: Building CNN Architectures with PyTorch•22 minutes
- Day 6: Regularization and Data Augmentation for CNNs•19 minutes
- Day 7: CNN Project – Image Classification on Fashion MNIST or CIFAR-10•28 minutes
1 assignment•Total 15 minutes
- Week 10: Convolutional Neural Networks (CNNs) - Assessment•15 minutes
In this module, we will explore RNNs and their ability to process sequential data. You will learn about advanced RNN architectures like LSTMs and GRUs, apply text preprocessing and word embeddings, and build sequence-to-sequence models. The module culminates with a project focused on either text generation or sentiment analysis.
What's included
8 videos1 assignment
8 videos•Total 166 minutes
- Introduction to Week 11 Recurrent Neural Networks (RNNs) and Sequence Modeling•1 minute
- Day 1: Introduction to Sequence Modeling and RNNs•34 minutes
- Day 2: Understanding RNN Architecture and Backpropagation Through Time (BPTT)•25 minutes
- Day 3: Long Short-Term Memory (LSTM) Networks•15 minutes
- Day 4: Gated Recurrent Units (GRUs)•7 minutes
- Day 5: Text Preprocessing and Word Embeddings for RNNs•24 minutes
- Day 6: Sequence-to-Sequence Models and Applications•43 minutes
- Day 7: RNN Project – Text Generation or Sentiment Analysis•18 minutes
1 assignment•Total 15 minutes
- Week 11: Recurrent Neural Networks (RNNs) and Sequence Modeling - Assessment•15 minutes
In this module, we will explore the cutting-edge Transformer architecture and attention mechanisms that have revolutionized NLP. You will gain hands-on experience working with pre-trained models like BERT and GPT, learning how to fine-tune them for real-world tasks like text summarization and translation.
What's included
8 videos1 assignment
8 videos•Total 135 minutes
- Introduction to Week 12 Transformers and Attention Mechanisms•1 minute
- Day 1: Introduction to Attention Mechanisms•15 minutes
- Day 2: Introduction to Transformers Architecture•18 minutes
- Day 3: Self-Attention and Multi-Head Attention in Transformers•21 minutes
- Day 4: Positional Encoding and Feed-Forward Networks•20 minutes
- Day 5: Hands-On with Pre-Trained Transformers – BERT and GPT•20 minutes
- Day 6: Advanced Transformers – BERT Variants and GPT-3•21 minutes
- Day 7: Transformer Project – Text Summarization or Translation•19 minutes
1 assignment•Total 15 minutes
- Week 12: Transformers and Attention Mechanisms - Assessment•15 minutes
In this module, we will dive into transfer learning, teaching you how to leverage pre-trained models for faster and more efficient model development. You will explore fine-tuning techniques for both computer vision and NLP tasks, addressing domain adaptation challenges, and apply your skills to a project focused on fine-tuning a model for a custom task.
What's included
8 videos1 reading3 assignments
8 videos•Total 140 minutes
- Introduction to Week 13 Transfer Learning and Fine-Tuning•1 minute
- Day 1: Introduction to Transfer Learning•15 minutes
- Day 2: Transfer Learning in Computer Vision•26 minutes
- Day 3: Fine-Tuning Techniques in Computer Vision•22 minutes
- Day 4: Transfer Learning in NLP•17 minutes
- Day 5: Fine-Tuning Techniques in NLP•26 minutes
- Day 6: Domain Adaptation and Transfer Learning Challenges•15 minutes
- Day 7: Transfer Learning Project – Fine-Tuning for a Custom Task•18 minutes
1 reading•Total 10 minutes
- Conclusion to the Course 'Deep Learning & Modern AI Architectures'New Reading•10 minutes
3 assignments•Total 90 minutes
- Full Course Practice Assessment•15 minutes
- Week 13: Transfer Learning and Fine-Tuning - Assessment•15 minutes
- Full Course Assessment•60 minutes
Earn a career certificate
Add this credential to your LinkedIn profile, resume, or CV. Share it on social media and in your performance review.
Instructor
Explore more from Machine Learning
Course
- Status: Free Trial
Course
- Status: Free TrialE
Edureka
Specialization
- Status: Free Trial
Course
Why people choose Coursera for their career
Frequently asked questions
The "Deep Learning & Modern AI Architectures" course offers a thorough exploration of deep learning techniques and architectures, including neural networks, convolutional neural networks (CNNs), recurrent neural networks (RNNs), and Transformers. This course is highly relevant for anyone looking to dive into cutting-edge AI, as deep learning and modern architectures power many of today’s most advanced applications in fields like computer vision, natural language processing, and speech recognition.
This course covers fundamental to advanced deep learning topics. Week 9 introduces the basics of neural networks, including concepts like forward propagation, loss functions, and backpropagation. Week 10 focuses on Convolutional Neural Networks (CNNs) for image-based tasks, while Week 11 delves into Recurrent Neural Networks (RNNs) for sequence data like text. Week 12 explores Transformers, a breakthrough architecture used in modern NLP tasks. Finally, Week 13 teaches transfer learning and fine-tuning techniques, helping you leverage pre-trained models for your own AI tasks.
After completing this course, you'll be proficient in building and training deep learning models using frameworks like TensorFlow, Keras, and PyTorch. You’ll be able to design and implement CNNs for image classification, RNNs for sequence modeling, and use Transformers for NLP tasks. You'll also understand how to apply transfer learning techniques to improve model efficiency. The course equips you with the skills needed to tackle a wide range of modern AI challenges.
More questions
Financial aid available,