Productionizing AI

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 you’ll explore data pipeline orchestration, machine and deep learning, including working with and finding shortcuts using artificial neural networks such as AutoML and AutoAI. You’ll 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.

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.

Chapter 1: Introduction to AI & the AI Ecosystem

Chapter Goal: Embracing the hype and the pitfalls, introduces the reader to current and emerging trends in AI and how many businesses and organisations are struggling to get machine and deep learning operationalized

No of pages: 30

Sub -Topics

1. The AI ecosystem2. Applications of AI

3. AI pipelines

4. Machine learning

5. Neural networks & deep learning

6. Productionizing AI

Chapter 2: AI Best Practise & DataOps

Chapter Goal: Help the reader understand the wider context for AI, key stakeholders, the importance of collaboration, adaptability and re-use as well as DataOps best practice in delivering high-performance solutions

No of pages: 20

Sub - Topics

1. Introduction to DataOps and MLOps

2. Agile development

3. Collaboration and adaptability

4. Code repositories

5. Module 4: Data pipeline orchestration

6. CI / CD

7. Testing, performance evaluation & monitoring

Chapter 3: Data Ingestion for AI

Chapter Goal: Inform on best practice and the right (cloud) data architectures and orchestration requirements to ensure the successful delivery of an AI project.

No of pages : 20

Sub - Topics: 1. Introduction to data ingestion

2. Data stores for AI

3. Data lakes, warehousing & streaming

4. Data pipeline orchestration

Chapter 4: Machine Learning on Cloud

Chapter Goal: Top-down ML model building from design thinking, through high level process, data wrangling, unsupervised clustering techniques, supervised classification, regression and time series approaches before interpreting results and algorithmic performance

No of pages: 20

Sub - Topics:

1. ML fundamentals

2. EDA & data wrangling

3. Supervised & unsupervised machine learning

4. Python Implementation

5. Unsupervised clustering, pattern & anomaly detection

6. Supervised classification & regression case studies: churn & retention modelling, risk engines, social media sentiment analysis

7. Time series forecasting and comparison with fbprophet

Chapter 5: Neural Networks and Deep Learning

Chapter Goal: Help the reader establish the right artificial neural network architecture, data orchestration and infrastructure for deep learning with TensorFlow, Keras and PyTorch on Cloud

No of pages: 40

Sub - Topics:

1. An introduction to deep learning

2. Stochastic processes for deep learning

3. Artificial neural networks

4. Deep learning tools & frameworks

5. Implementing a deep learning model

6. Tuning a deep learning model

7. Advanced topics in deep learning

Chapter 6: The Employer’s Dream: AutoML, AutoAI and the rise of NoLo UIs

Chapter Goal: Building on acquired ML and DL skills, learn to leverage the growing ecosystem of AutoML, AutoAI and No/Low code user interfacesNo of pages: 20

Sub - Topics:

1. AutoML

2. Optimizing the AI pipeline

3. Python-based libraries for automation

4. Case Studies in Insurance, HR, FinTech & Trading, Cybersecurity and Healthcare5. Tools for AutoAI: IBM Cloud Pak for Data, Azure Machine Learning, Google Teachable Machines

Chapter 7: AI Full Stack: Application Development

Chapter Goal: Starting from key business/organizational needs for AI, identify the correct solution and technologies to develop and deliver “Full Stack AI”

No of pages: 20

Sub - Topics:

6. Introduction to AI application development

7. Software for AI development

8. Key Business applications of AI:

• ML Apps

• NLP Apps• DL Apps

4. Designing & building an AI application

Chapter 8: AI Case Studies

Chapter Goal: A comprehensive (multi-sector, multi-functional) look at the main AI use uses in 2022

No of pages: 20

Sub - Topics:

1. Industry case studies

2. Telco solutions

3. Retail solutions

4. Banking & financial services / fintech solutions

5. Oil & gas / energy & utilities solutions

6. Supply chain solutions

7. HR solutions

8. Healthcare solutions

9. Other case studies

Chapter 9: Deploying an AI Solution (Productionizing & Containerization)Chapter Goal: A practical look at “joining the dots” with full-stack deployment of Enterprise AI on Cloud

No of pages: 20

Sub - Topics:

1. Productionizing an AI application

2. AutoML / AutoML

3. Storage & Compute4. Containerization

5. The final frontier…