Deep Learning: Build & Optimize Neural Networks

位教师：EDUCBA

访问权限由 Coursera Learning Team 提供

6个模块

深入了解一个主题并学习基础知识。

2 周完成

在 10 小时一周

灵活的计划

自行安排学习进度

6个模块

深入了解一个主题并学习基础知识。

2 周完成

在 10 小时一周

灵活的计划

自行安排学习进度

您将学到什么

Build and optimize deep neural networks using PyTorch.
Apply AI models to vision, NLP, and recommendation tasks.
Implement attention and transformer architectures effectively.

您将获得的技能

要了解的详细信息

可分享的证书

添加到您的领英档案

作业

22 项作业

授课语言：英语（English）

了解顶级公司的员工如何掌握热门技能

了解关于 Coursera for Business 的更多信息

Petrobras, TATA, Danone, Capgemini, P&G 和 L'Oreal 的徽标

该课程共有6个模块

By the end of this course, learners will differentiate core AI concepts, construct deep neural networks, apply image and text models, develop attention-based NLP systems, and design recommender solutions.

This hands-on course takes learners from the foundations of machine learning and deep learning to advanced implementations across computer vision, natural language processing, tabular prediction, and recommendation systems. Through guided lessons, coding exercises, and real-world case studies, learners will gain practical expertise with industry-standard tools like Jupyter, Google Colab, and PyTorch. What makes this course unique is its step-by-step structure: starting with beginner-friendly concepts, gradually progressing into building robust neural networks, and finally applying advanced architectures like transformers and attention mechanisms. Each module emphasizes practical coding, ensuring learners don’t just understand theory but also implement and optimize models in real projects. Completing this course equips learners with the skills to analyze data, engineer features, build scalable models, and evaluate performance—making them job-ready for roles in AI, deep learning engineering, and data science.

This module introduces learners to the core principles of machine learning and deep learning, exploring their methods, applications, and the evolution from perceptrons to deep neural networks.

涵盖的内容

12个视频3个作业

12个视频总计86分钟

Introduction to Hands on Deeplearning 4分钟
What is Machine Learning 10分钟
Popular ML Methods 6分钟
What is Deep Learning 7分钟
Applications of Deeplearning 10分钟
Recommendations 10分钟
Basic Concept of Deeplearning 1分钟
Perception 6分钟
Neural Network 7分钟
Universal Approximations Theorem 8分钟
Deep Neural Network 12分钟
Deep Neural Network Continue 5分钟

3个作业总计50分钟

Graded-Foundations of Deep Learning 30分钟
The World of AI & ML 10分钟
From Basics to Neural Networks 10分钟

This module provides hands-on exposure to essential coding platforms, tools, and frameworks like Jupyter, Google Colab, and PyTorch, while building foundational skills with tensors, gradients, and basic networks.

涵盖的内容

15个视频4个作业

15个视频总计95分钟

Getting Started 2分钟
Where to write Code 2分钟
Jupiter Notebook 9分钟
Google Colab 10分钟
Pytorch 2分钟
Tensors 7分钟
Tensors Continue 9分钟
Gradients 6分钟
MNIST Example 9分钟
Check Sample 7分钟
Hidden Layer 9分钟
Interface on a Digit 5分钟
Transfer-Learning-Overview 5分钟
What is Transfer Learning 7分钟
CS231n Convolutional Neural Networks 8分钟

4个作业总计60分钟

Graded-Getting Started with Tools 30分钟
Setting Up Your Workspace 10分钟
First Steps with Tensors 10分钟
Building Layers & Interfaces 10分钟

This module explores image classification through practical case studies, guiding learners to preprocess, transform, and visualize datasets, then build, train, and test deep neural networks on benchmarks like MNIST and CIFAR-10.

涵盖的内容

18个视频4个作业

18个视频总计166分钟

Download Dataset 7分钟
Transform the Data 13分钟
Visualize the Data 10分钟
Define the Model 9分钟
Add a Few Final Layers 10分钟
Train the Model 7分钟
Test the Model 6分钟
What About CIFAR 6分钟
Image Classifier on Cifar 10 Dataset 8分钟
Download and Load Our Dataset 11分钟
Train and Test Dataset 13分钟
Define Our Neural Network 8分钟
Working on Image 11分钟
Input and Output 8分钟
Define Our Loss Function 12分钟
Train Data in Enumerate 10分钟
Train Data in Enumerate Continue 7分钟
Test the Neural Network on the Test Image 10分钟

4个作业总计60分钟

Graded-Image Classification in Action 30分钟
Preparing and Transforming Data 10分钟
Training and Testing Models 10分钟
Building Robust Neural Networks 10分钟

This module introduces natural language processing (NLP) tasks, including text classification with CNNs and text generation with transformers, focusing on preparing textual data, building models, and evaluating results.

涵盖的内容

15个视频4个作业

15个视频总计129分钟

Intro to Text Classifier 6分钟
Text Classification Using CNN 9分钟
Prepare the Data 7分钟
Build the Model 8分钟
Build the Model Continue 13分钟
More on Build the Model 4分钟
Define a Loss Function 7分钟
Define a Loss Function Continue 10分钟
More on Define a Loss Function 6分钟
Evaluate or Test the Model 6分钟
Intro to Text Generation 15分钟
Text Generation-Transformers 10分钟
Text Generation-Transformers Continue 10分钟
Transformers-Architectures 10分钟
Transformers-Architectures Continue 8分钟

4个作业总计60分钟

Deep Learning for Text 30分钟
Text Classification with CNNs 10分钟
Optimizing Models 10分钟
Text Generation with Transformers 10分钟

This module dives deeper into NLP using attention-based architectures, covering sequence-to-sequence models for text translation, encoder-decoder frameworks, and best practices for training and evaluation.

涵盖的内容

14个视频4个作业

14个视频总计122分钟

Word-Generation 6分钟
Word-Generation Continue 10分钟
Text-Generation 4分钟
Intro to Text Translation 5分钟
Loading-Data 10分钟
Preparing-Data 5分钟
Encoder-Attention Part 1 10分钟
Encoder-Attention Part 2 9分钟
Encoder-Attention Part 3 7分钟
Decoder 12分钟
Train-Eval-Functions 11分钟
Train-Eval-Functions Continue 10分钟
Training-Fixes 13分钟
Training-Evaluation 10分钟

4个作业总计60分钟

Graded-Advanced NLP with Attention 30分钟
Generating Words & Sequences 10分钟
Building Translation Models 10分钟
Training & Evaluation 10分钟

This module extends deep learning applications to structured tabular data and recommender systems, demonstrating predictive modeling and approaches like collaborative and content-based filtering.