Atnaujinkite slapukų nuostatas

El. knyga: Productionizing AI: How to Deliver AI B2B Solutions with Cloud and Python

  • Formatas: EPUB+DRM
  • Išleidimo metai: 24-Dec-2022
  • Leidėjas: APress
  • Kalba: eng
  • ISBN-13: 9781484288177
Kitos knygos pagal šią temą:
Productionizing AI: How to Deliver AI B2B Solutions with Cloud and PythonDidesnis paveikslėlis
  • Formatas: EPUB+DRM
  • Išleidimo metai: 24-Dec-2022
  • Leidėjas: APress
  • Kalba: eng
  • ISBN-13: 9781484288177
Kitos knygos pagal šią temą:

DRM apribojimai

  • Kopijuoti:

    neleidžiama

  • Spausdinti:

    neleidžiama

  • El. knygos naudojimas:

    Skaitmeninių teisių valdymas (DRM)
    Leidykla pateikė šią knygą šifruota forma, o tai reiškia, kad norint ją atrakinti ir perskaityti reikia įdiegti nemokamą programinę įrangą. Norint skaityti šią el. knygą, turite susikurti Adobe ID . Daugiau informacijos  čia. El. knygą galima atsisiųsti į 6 įrenginius (vienas vartotojas su tuo pačiu Adobe ID).

    Reikalinga programinė įranga
    Norint skaityti šią el. knygą mobiliajame įrenginyje (telefone ar planšetiniame kompiuteryje), turite įdiegti šią nemokamą programėlę: PocketBook Reader (iOS / Android)

    Norint skaityti šią el. knygą asmeniniame arba „Mac“ kompiuteryje, Jums reikalinga  Adobe Digital Editions “ (tai nemokama programa, specialiai sukurta el. knygoms. Tai nėra tas pats, kas „Adobe Reader“, kurią tikriausiai jau turite savo kompiuteryje.)

    Negalite skaityti šios el. knygos naudodami „Amazon Kindle“.

This book is a guide to productionizing AI solutions using best-of-breed cloud services with workarounds to lower costs. Supplemented with step-by-step instructions covering data import through wrangling to partitioning and modeling through to inference and deployment, and augmented with plenty of Python code samples, the book has been written to accelerate the process of moving from script or notebook to app.





From an initial look at the context and ecosystem of AI solutions today, the book drills down from high-level business needs into best practices, working with stakeholders, and agile team collaboration. From there youll explore data pipeline orchestration, machine and deep learning, including working with and finding shortcuts using artificial neural networks such as AutoML and AutoAI. Youll also learn about the increasing use of NoLo UIs through AI application development, industry case studies, and finally a practical guide to deploying containerized AI solutions.





The book is intended for those whose role demands overcoming budgetary barriers or constraints in accessing cloud credits to undertake the often difficult process of developing and deploying an AI solution.





What You Will Learn













Develop and deliver production-grade AI in one month Deploy AI solutions at a low cost Work around Big Tech dominance and develop MVPs on the cheap Create demo-ready solutions without overly complex python scripts/notebooks





















 Who this book is for:





Data scientists and AI consultants with programming skills in Python and driven to succeed in AI.
About the Author xvii
About the Technical Reviewer xix
Preface xxi
Prologue xxiii
Chapter 1 Introduction to Al and the Al Ecosystem
1(40)
The Al Ecosystem
2(11)
The Hype Cycle
2(1)
Historical Context
3(1)
Al - Some Definitions
4(1)
Al Today
4(2)
What Is Artificial Intelligence
6(1)
Cloud Computing
7(1)
CSPs-What Do They Offer?
7(2)
The Wider Al Ecosystem
9(1)
Full-Stack Al
10(1)
Al Ethics and Risk: Issues and Concerns
11(1)
The Al ecosystem: Hands-on Practise
11(2)
Applications of Al
13(7)
Machine Learning
13(1)
Deep Learning
14(2)
Natural Language Processing (NLP)
16(1)
Cognitive Robotic Process Automation (CRPA)
17(1)
Other Al Applications
18(1)
Al Applications: Hands-on Practice
19(1)
Data Ingestion and Al Pipelines
20(5)
Al Engineering
21(1)
What Is a Data Pipeline?
21(1)
Extract, Transform, and Load (ETL)
22(1)
Data Wrangling
22(1)
Performance Benchmarking
23(1)
Al Pipeline Automation - AutoAl
24(1)
Build Your Own Al Pipeline: Hands-on Practice
25(1)
Neural Networks and Deep Learning
25(8)
Machine Learning
26(1)
What Is a Neural Network?
27(1)
The Simple Perceptron
28(1)
Deep Learning
28(2)
Neural Networks - terminology
30(1)
Tools for Deep Learning
31(1)
Introduction to Neural Networks and DL: Hands-on Practice
31(2)
Productionizing Al
33(6)
Compute and Storage
33(1)
The CSPs - Why No-one Can Be Successful in Al Without Investing in Amazon, Microsoft, or Google
34(2)
Containerization
36(1)
Productionizing Al: Hands-on Practice
37(2)
Wrap-up
39(2)
Chapter 2 Al Best Practice and DataOps
41(34)
Introduction to DataOps and MLOps
42(5)
DataOps
42(1)
The Data "Factory"
43(1)
The Problem with Al: From DataOps to MLOps
43(2)
Enterprise Al
45(1)
GCP/BigQuery: Hands-on Practice
45(1)
Event Streaming with Kafka: Hands-on Practice
46(1)
Agile
47(6)
Agile Teams and Collaboration
47(1)
Development/Product Sprints
48(2)
Benefits of Agile
50(1)
Adaptability
50(1)
React.js: Hands-on Practice
51(1)
VueJS: Hands-on Practise
52(1)
Code Repositories
53(7)
Git and GitHub
53(1)
Version Control
54(1)
Branching and Merging
55(1)
Git Workflows
56(1)
GitHub and Git: Hands-on Practice
57(2)
Deploying an App to GitHub Pages: Hands-on Practice
59(1)
Continuous Integration and Continuous Delivery (CI/CD)
60(6)
CI/CD in DataOps
60(1)
Introduction to Jenkins
61(1)
Maven
62(1)
Containerization
63(1)
Play With Docker: Hands-on Practice
64(2)
Testing, Performance Evaluation, and Monitoring
66(8)
Selenium
66(1)
TestNG
67(1)
Issue Management
68(2)
Monitoring and Alerts
70(2)
Jenkins CI/CD and Selenium Test Scripts: Hands-on Practice
72(2)
Wrap-up
74(1)
Chapter 3 Data Ingestion for Al
75(34)
Introduction to Data Ingestion
75(10)
Data Ingestion - The Challenge Today
76(1)
The Al Ladder
76(1)
Cloud Architectures/Cloud "Stack"
77(1)
Scheduled (OLAP) vs. Streaming (OLTP) Data
78(2)
Data Types (Structured vs. Unstructured)
80(1)
File Types
81(1)
Automated Data Ingestion: Hands-on Practice
82(1)
Working with Parquet: Hands-on Practise
83(2)
Data Stores for Al
85(7)
Data Stores: Data Lakes and Data Warehouses
85(2)
Scoping Project Data Requirements
87(1)
OLTP/OLAP - Determining the Best Approach
88(1)
ETLvs. ELT
88(1)
SQL vs. NoSQL Databases
89(1)
Elasticity vs. Scalability
90(1)
Data Stores for Al: Hands-on Practice
90(2)
Cloud Services for Data Ingestion
92(5)
Cloud (SQL) Data Warehouses
92(1)
Data Lake Storage
92(2)
Stream Processing and Stream Analytics
94(1)
Simple Data Streaming: Hands-on Practise
95(2)
Data Pipeline Orchestration - Best Practice
97(10)
Storage Considerations
97(1)
Data Ingestion Schedules
98(2)
Building a Delivery Pipeline
100(6)
Data Pipeline Orchestration: Hands-on Practice
106(1)
Wrap-up
107(2)
Chapter 4 Machine Learning on Cloud
109(24)
ML Fundamentals
110(1)
Supervised Machine Learning
110(3)
Classification and Regression
110(1)
Time Series Forecasting
111(1)
Introduction to fbprophet: Hands-on Practice
112(1)
Unsupervised Machine Learning
113(2)
Clustering
113(1)
Dimensionality Reduction
114(1)
Unsupervised Machine Learning (Clustering): Hands-on Practice
114(1)
Semisupervised Machine Learning
115(1)
Machine Learning Implementation
115(1)
Exploratory Data Analysis (EDA)
116(1)
Data Wrangling
117(5)
Feature Engineering
118(1)
Shuffling and Data Partitioning/Splitting
119(1)
Sampling
120(1)
End-to-End Wrangling: Hands-on Practice
121(1)
Algorithmic Modelling
122(3)
Performance Benchmarking
125(4)
Continual Improvement
127(1)
Machine Learning Classifiers: Hands-on Practice
128(1)
Model Selection, Deployment, and Inference
129(1)
Inference: Hands-on Practice
130(1)
Reinforcement Learning
130(1)
Wrap-up
131(2)
Chapter 5 Neural Networks and Deep Learning
133(54)
Introduction to Deep Learning
134(5)
What Is Deep Learning
134(1)
Deep Learning - Why Now?
135(1)
Al and Deep Learning Hype Cycle
136(1)
High-Level Architectures
137(1)
TensorFlow Playground: Hands-on Practice
138(1)
Stochastic Processes
139(4)
Generative vs. Discriminative
139(1)
Random Walks
140(1)
Markov Chains and Markov Processes
141(1)
Other Stochastic Processes: Martingales
141(1)
Implementing a Random Walk in Python: Hands-on Practice
142(1)
Introduction to Neural Networks
143(13)
Artificial Neural Networks (ANNs)
143(1)
The Simple Perceptron
144(1)
Multilayer Perceptron (MLP)
145(1)
Convolutional Neural Networks (CNN)
146(1)
Recurrent Neural Networks (RNN)
147(2)
Other Types of Neural Networks
149(4)
A Simple Deep Learning Solution - MNIST: Hands-on Practice
153(2)
Autoencoders in Keras: Hands-on Practice
155(1)
Deep Learning Tools
156(3)
Tools for Deep Learning
156(1)
TensorFlow
156(1)
Keras
157(1)
PyTorch
158(1)
Other Important Deep Learning Tools
158(1)
Frameworks for Deep Learning and Implementation
159(13)
Tensors
160(1)
Key TensorFlow Concepts
160(1)
The Deep Learning Modeling Lifecycle
161(1)
Sequential and Functional Model APIs
162(1)
Implementing a CNN
163(2)
Implementing an RNN
165(3)
Neural Networks - Terminology
168(1)
Computing the Output of a Multilayer Neural Network
168(2)
Convolutional Neural Networks with Keras and TensorFlow: Hands-on Practice
170(1)
Recurrent Neural Networks - Time Series Forecasting: Hands-on Practice
171(1)
Tuning a DL Model
172(13)
Activation Functions
172(2)
Gradient Descent and Backpropagation
174(1)
Other Optimization Algorithms
175(1)
Loss Functions
176(2)
Improving DL Performance
178(1)
Deep Learning Best Practice - Hyperparameters
179(6)
Wrap-up
185(2)
Softmax: Hands-on Practice
185(1)
Early Stopping: Hands-on Practice
186(1)
Chapter 6 AutoML, AutoAl, and the Rise of NoLo Uls
187(24)
Machine Learning: Process Recap t
189(1)
Global Search Algorithms
190(2)
Bayesian Optimization and Inference
191(1)
Bayesian Inference: Hands-on Practice
191(1)
Python-Based Libraries for Automation
192(4)
PyCaret
192(1)
auto-sklearn
193(1)
AutO-WEKA
194(1)
TPOT
194(1)
Python Automation with TPOT: Hands-on Practice
195(1)
AutoAl Tools and Platforms
196(15)
IBM Cloud Pakfor Data
196(2)
Azure Machine Learning
198(1)
Google Cloud Vertex Al
199(2)
AWS SageMaker Autopilot
201(1)
TensorFlow Extended (TFX)
202(1)
Wrap-up
203(1)
AutoAl with IBM Cloud Pak for Data: Hands-on Practice
203(2)
Healthcare diagnostics with Google Teachable Machines: Hands-on Practice
205(1)
TFX and Vertex Al Pipelines: Hands-on Practice
206(2)
Azure Video Analyzer: Hands-on Practice
208(3)
Chapter 7 Al Full Stack: Application Development
211(36)
Introduction to Al Application Development
212(10)
Developing an Al Solution
212(1)
Al Apps - Up and Running
213(1)
APIs and Endpoints
214(1)
Distributed Processing and Clusters
215(3)
Virtual Environments
218(1)
Running Python from Terminal: Hands-on Practice
219(1)
API Web Services and Endpoints: Hands-on Practice
220(1)
Al Accelerators - GPUs: Hands-on Practise
221(1)
Software and Tools for Al Development
222(12)
Al Needs Data and Cloud
222(3)
Cloud Platforms
225(3)
Python-Based Uls
228(3)
Other Al Software Vendors
231(1)
Introduction to Dash: Hands-on Practice
232(1)
Flask: Hands-on Practice
233(1)
Introduction to Django: Hands-on Practice
233(1)
ML Apps
234(6)
Developing Machine Learning Applications
235(1)
Customer Experience
236(1)
Fraud Detection and Cybersecurity
237(1)
Operations Management, Decision, and Business Support
237(1)
Risk Management, and Portfolio and Asset Optimization
238(1)
Developing a Recommendation Engine: Hands-on Practice
238(1)
Portfolio Optimization Accelerator: Hands-on Practise
239(1)
DL Apps
240(5)
Developing Deep Learning Applications
240(2)
Key Deep Learning Apps
242(1)
Full-Stack Deep Learning: Hands-on Practice
243(2)
Wrap-up
245(2)
Chapter 8 Al Case Studies
247(42)
Industry Case Studies
248(3)
Business/Organizational Demand for Al
248(1)
Al Enablers
248(1)
Al Solutions by Vertical Industry
249(1)
Al Use Cases - Solution Frameworks
249(1)
Solution Architectures
250(1)
Telco Solutions
251(8)
Specific Challenges
252(1)
Solution Categories
252(1)
Real-time Dashboards
253(2)
Sentiment Analysis
255(1)
Predictive Analytics
256(1)
Connecting to the Twitter API from Python
257(1)
Twitter API and Basic Sentiment Analysis: Hands-on Practice
258(1)
Retail Solutions
259(6)
Challenges in the Retail Industry
259(1)
Churn and Retention Modelling
260(2)
Online Retail Predictive Analytics with GCP BigQuery: Hands-on Practice
262(1)
Predicting Customer Churn: Hands-on Practise
263(1)
Social Network Analysis: Hands-on Practise
264(1)
Banking and Financial Services/FinTech Solutions
265(6)
Industry Challenges
265(2)
Fraud Detection
267(2)
AWS Fraud Detection with AWS SageMaker: Hands-on Practice
269(2)
Supply Chain Solutions
271(5)
Challenges Across Supply Chains
271(1)
Predictive Analytics Solutions
272(1)
Supply Chain Optimization and Prescriptive Analytics
273(1)
Supply Chain Optimization with IBM CloudPak/Watson Studio: Hands-on Practice
274(2)
Oil and Gas/Energy and Utilities Solutions
276(2)
Challenges in Energy, Oil, and Gas Sectors
276(1)
Al Solutions in Energy - An Opportunity or a Threat?
276(2)
Healthcare and Pharma Solutions
278(1)
Healthcare-The Al Gap
278(1)
Healthcare and Pharma Solutions
279(1)
HR Solutions
279(5)
HR in 2002
280(1)
Sample HR Solutions
281(2)
HR Employee Attrition: Hands-on Practice
283(1)
Other Case Studies
284(4)
Public Sector and Government
284(1)
Manufacturing
285(1)
Cybersecurity
285(1)
Insurance/Telematics
286(1)
Legal
286(1)
Dall-E for the Creative Arts: Hands-on Practise
287(1)
Wrap-up
288(1)
Chapter 9 Deploying an Al Solution (Productionizing and Containerization)
289(30)
Productionizing an Al Application
290(6)
Typical Barriers to Production
290(1)
Cloud/CSP Roulette
291(1)
Simplifying the Al Challenge - Start Small, Stay Niche
292(2)
Database Management in Python: Hands-on Practice
294(1)
App Building on GCP: Hands-on Practice
295(1)
PowerBI - Python Handshake: Hands-on Practice
296(1)
Al Project Lifecycle
296(7)
Design Thinking Through to Agile Development
296(1)
Driving Development Through Hypothesis
297(1)
Collaborate, Test, Measure, Repeat
298(1)
Continual Process Improvement
299(1)
Data drift
300(1)
Automated Retraining
301(1)
Hosting on Heroku - End-to-End: Hands-on Practice
302(1)
Enabling Engineering and Infrastructure
303(4)
The Al Ecosystem - The Al Cloud Stack
303(1)
Data Lake Deployment - Best Practice
304(1)
Data Pipeline Operationalization and Orchestration
305(2)
Big Data Engines and Parallelization
307(4)
Dask
307(1)
Leveraging S3 File Storage: Hands-on Practise
308(1)
Apache Spark Quick Start on Databricks: Hands-on Practice
309(1)
Dask Parallelization: Hands-on Practice
310(1)
Full Stack and Containerization the final frontier
311(8)
Full Stack Al - React and Flask Case Study
311(1)
Deploying on Cloud with a Docker Container
312(1)
Implementing a Continuous Delivery Pipeline
313(1)
Wrap-up
314(1)
DL App deployment with Streamlit and Heroku: Hands-on Practice
314(1)
Deploying on Azure with a Docker Container: Hands-on Practice
315(4)
Chapter 10 Natural Language Processing
319(40)
Introduction to NLP
320(8)
NLP Fundamentals
320(2)
NLP Goals and Sector-specific Use Cases
322(1)
The NLP Lifecycle
323(4)
Creating a Word Cloud: Hands-on Practice
327(1)
Preprocessing and Linguistics
328(8)
Preprocessing/Initial Cleaning
328(1)
Linguistics and Data Transformation
329(6)
Text Parsing with NLTK: Hands-on Practice
335(1)
Text Vectorization, Word Embeddings, and Modelling in NLP
336(12)
Rule-Based/Frequency-Based Embedding
337(3)
Word Embeddings/Prediction-Based Embedding
340(2)
NLP Modeling
342(3)
Word Embeddings: Hands-on Practice
345(1)
Seq2Seq: Hands-on Practice
346(1)
PyTorch NLP: Hands-on Practice
347(1)
Tools and Applications of NLP
348(11)
Python Libraries
349(1)
NLP Applications
350(3)
NLP 2.0
353(2)
Wrap-up
355(1)
WATSON Assistant Chatbot/IVA: Hands-on Practice
355(2)
Transformers for Chatbots: Hands-on Practice
357(2)
Postscript 359(4)
Index 363
Barry Walsh is a software-delivery consultant and AI trainer at Pairview with a background in exploiting complex business data to optimize and de-risk energy assets at ABB/Ventyx, Infosys, E.ON, Centrica, and his own start-up ce.tech. He has a proven track record of providing consultancy services in Data Science, BI, and Business Analysis to businesses in Energy, IT, FinTech, Telco, Retail, and Healthcare, Barry has been at the apex of analytics and AI solutions delivery for 20 years. Besides being passionate about Enterprise AI, Barry spends his spare time with his wife and 8-year-old son, playing the piano, riding long bike rides (and a marathon on a broken toe this year), eating out whenever possible or getting his daily coffee fix.
Daugiau apie elektronines knygas Daugiau apie elektronines knygas
Pastovi nuoroda: https://www.kriso.lt/db/97814842881776e.html
Raktažodžiai: