Learning Deep Learning: Unit 2

Learning Deep Learning: Unit 2

This course is part of Learning Deep Learning Specialization

Instructors: Pearson

Access provided by Interbank

1 module

Gain insight into a topic and learn the fundamentals.

Intermediate level

Recommended experience

8 hours to complete

Flexible schedule

Learn at your own pace

1 module

Gain insight into a topic and learn the fundamentals.

Intermediate level

Recommended experience

8 hours to complete

Flexible schedule

Learn at your own pace

What you'll learn

Build and optimize convolutional neural networks for advanced image classification tasks using TensorFlow and PyTorch.
Apply recurrent neural networks and LSTMs to sequential data problems, including time series forecasting and text autocompletion.
Develop neural language models and implement word embeddings for robust natural language processing.
Design and implement encoder-decoder architectures and Transformer models for machine translation and sequence-to-sequence tasks.

Skills you'll gain

Tools you'll learn

Details to know

Shareable certificate

Add to your LinkedIn profile

Assessments

4 assignments

Taught in English

See how employees at top companies are mastering in-demand skills

Learn more about Coursera for Business

logos of Petrobras, TATA, Danone, Capgemini, P&G and L'Oreal

Build your subject-matter expertise

This course is part of the Learning Deep Learning Specialization

When you enroll in this course, you'll also be enrolled in this Specialization.

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 course covers advanced deep learning topics, including Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and modern language models. You will learn techniques for image classification, time series prediction, and natural language processing. The course includes building and optimizing CNNs for image recognition, using architectures such as AlexNet, VGGNet, GoogLeNet, and ResNet, and working with pre-trained models. You will also work with RNNs and LSTMs for tasks like forecasting and text autocompletion. The curriculum covers neural language models, word embeddings (such as Word2vec and wordpieces), encoder-decoder architectures, attention mechanisms, and Transformers for machine translation. Hands-on projects using TensorFlow and PyTorch will help you develop practical skills for solving real-world problems in computer vision and language processing.

This module provides a comprehensive introduction to advanced deep learning techniques for processing images and natural language. It covers convolutional neural networks for image classification, including architectures like AlexNet, VGGNet, GoogLeNet, and ResNet. The module then explores recurrent neural networks and LSTMs for time series and sequential data, followed by neural language models and word embeddings. Finally, it introduces encoder-decoder architectures, attention mechanisms, and Transformer models for neural machine translation, with practical implementations in TensorFlow and PyTorch throughout.

What's included

44 videos4 assignments

44 videos Total 341 minutes

Topics 1 minute
The CIFAR-10 Dataset 4 minutes
Convolutional Layer 9 minutes
Building a Convolutional Neural Network 14 minutes
Programming Example: Image Classification Using CNN with TensorFlow 9 minutes
Programming Example: Image Classification Using CNN with PyTorch 9 minutes
AlexNet 6 minutes
VGGNet 5 minutes
GoogLeNet 5 minutes
ResNet 6 minutes
Programming Example: Using a Pretrained Network with TensorFlow 4 minutes
Programming Example: Using a Pretrained Network with PyTorch 5 minutes
Amplifying Your Data 4 minutes
Efficient CNNs 4 minutes
Lesson 4 Summary 3 minutes
Topics 1 minute
Problem Types Involving Sequential Data 7 minutes
Recurrent Neural Networks 8 minutes
Programming Example: Forecasting Book Sales with TensorFlow 9 minutes
Programming Example: Forecasting Book Sales with PyTorch 11 minutes
Backpropagation Through Time and Keeping Gradients Healthy 9 minutes
Long Short-Term Memory 10 minutes
Autoregression and Beam Search 7 minutes
Programming Example: Text Autocompletion with TensorFlow 14 minutes
Programming Example: Text Autocompletion with PyTorch 16 minutes
Lesson 5 Summary 2 minutes
Topics 1 minute
Language Models 13 minutes
Word Embeddings 12 minutes
Programming Example: Language Model and Word Embeddings with TensorFlow 12 minutes
Programming Example: Language Model and Word Embeddings with PyTorch 18 minutes
Word2vec 6 minutes
Programming Example: Using Pretrained GloVe Embeddings 7 minutes
Handling Out-of-Vocabulary Words with Wordpieces 3 minutes
Lesson 6 Summary 2 minutes
Topics 1 minute
Encoder–Decoder Network for Neural Machine Translation 4 minutes
Programming Example: Neural Machine Translation with TensorFlow 24 minutes
Programming Example: Neural Machine Translation with PyTorch 22 minutes
Attention 8 minutes
The Transformer 8 minutes
Programming Example: Machine Translation Using Transformer with TensorFlow 7 minutes
Programming Example: Machine Translation Using Transformer with PyTorch 8 minutes
Lesson 7 Summary 2 minutes

4 assignments Total 120 minutes

Convolutional Neural Networks (CNN) and Image Classification Quiz 30 minutes
Recurrent Neural Networks (RNN) and Time Series Prediction Quiz 30 minutes
Neural Language Models and Word Embeddings Quiz 30 minutes
Encoder–Decoder Networks, Attention, Transformers, and Neural Machine Translation Quiz 30 minutes