深度学习领域取得了指数级的发展,像BERT、GPT-3、ResNet等ML模型的足迹也在不断扩大。虽然它们工作得很好,但在生产中训练和部署这些大型(且不断增长的)模型是昂贵的。你可能想在智能手机上部署你的面部滤镜模型,让你的用户在他们的自拍上添加一个小狗滤镜。但它可能太大或太慢,或者您可能想提高基于云的垃圾邮件检测模型的质量,但又不想花钱购买更大的云VM来承载更精确但更大的模型。如果您的模型没有足够的标记数据,或者不能手动调优您的模型,该怎么办? 所有这些都是令人生畏的!
如果您可以使您的模型更高效: 使用更少的资源(模型大小、延迟、训练时间、数据、人工参与),并提供更好的质量(准确性、精确度、召回等),会怎么样呢?这听起来太棒了! 但如何?
这本书将通过在谷歌研究,Facebook人工智能研究(FAIR),和其他著名的人工智能实验室使用算法和技术的研究人员和工程师训练和部署他们的模型,设备从大型服务器端机器到微型微控制器。在这本书中,我们提出了一个基本的平衡,以及实践知识,以充分赋能你继续前进,并优化你的模型训练和部署工作流,这样你的模型表现和以前一样好或更好,与一小部分资源。我们还将深入介绍流行的模型、基础设施和硬件,以及具有挑战性的项目,以测试您的技能。
https://efficientdlbook.com/
目录内容:
Part I: 高效深度学习导论 Introduction to Efficient Deep Learning
导论 Introduction
Introduction to Deep Learning
Efficient Deep Learning
Mental Model of Efficient Deep Learning
Summary
Part II: 效率技术 Effciency Techniques
压缩技术导论 Introduction to Compression Techniques
An Overview of Compression
Quantization
Exercises: Compressing images from the Mars Rover
Project: Quantizing a Deep Learning Model
Summary
学习技术导论 Introduction to Learning Techniques
Project: Increasing the accuracy of an speech identification model with Distillation.
Project: Increasing the accuracy of an image classification model with Data Augmentation.
Project: Increasing the accuracy of a text classification model with Data Augmentation.
Learning Techniques and Efficiency
Data Augmentation
Distillation
Summary
高效架构 Efficient Architectures
Project: Project: Snapchat-Like Filters for Pets
Project: News Classification Using RNN and Attention Models
Project: Using pre-trained embeddings to improve accuracy of a NLP task.
Motivation
Embeddings for Smaller and Faster Models
Learn Long-Term Dependencies Using Attention
Efficient On-Device Convolutions
Summary
自动化 Automation
Project: Layer-wise Sparsity to achieve a pareto optimal model.
Project: Searching over model architectures for boosting model accuracy.
Project: Multi-objective tuning to get a smaller and more accurate model.
Motivation
Hyper-Parameter Tuning
AutoML
Compression Search
高级压缩技术 Advanced Compression Techniques
Pruning
Clustering / Matrix Factorization
Weight Sharing
Project: Comparing Compression Techniques for optimizing a speech detection model.
高级学习技术 Advanced Learning Techniques
Contrastive Learning
Project: Learning to classify with 10% labels.
Federated Learning
Part 3 - Applied Deep Dives
Deep-Dives: Tensorflow Platforms
Project: Training BERT efficiently with TPUs.
Project: Face recognition on the web with TensorFlow.JS.
Project: Speech detection on a microcontroller with TFMicro.
Project: Benchmarking a tiny on-device model with TFLite.
Mobile
Microcontrollers
Web
Google Tensor Processing Unit (TPU)
Summary
Deep-Dives: Efficient Models
Project: Efficient speech detection models.
Project: Comparing efficient mobile models on Mobile.
Project: Training efficient BERT models.
BERT
MobileNet
EfficientNet architectures
Speech Detection
Part 4 - Software Infrastructure
Software Infrastructure
Tensorflow Ecosystem
PyTorch Ecosystem
iOS Ecosystem
专知便捷查看
便捷下载,请关注专知公众号(点击上方蓝色专知关注)
后台回复“EDLF” 就可以获取《【2022新书】高效深度学习,Efficient Deep Learning Book》》专知下载链接