[PDF][PDF] Introduction

RRM Coleman - Say It Loud!, 2013‏ - library.oapen.org
Now we demand a chance to do things for ourself We're tired ofbeatin our head against the
wall Say it loud, I'm Black and I'm proud.—James Brown," Say It Loud" The past three …

Motivation and Best Practices for Machine Learning Designers and Testers

S Ackerman, G Barash, E Farchi, O Raz… - Theory and Practice of …, 2024‏ - Springer
This chapter highlights best practices and pitfalls in the development of ML systems.
Following the best practices and avoiding the pitfalls presented should increase the …

Sequential Drift Detection

S Ackerman, G Barash, E Farchi, O Raz… - Theory and Practice of …, 2024‏ - Springer
This chapter discusses drift detection in the context of data observed in a time-ordered
sequence, as opposed to the static datasets in Chaps. 7 and 8. It covers concepts including …

Drift Detection by Measuring Distribution Differences

S Ackerman, G Barash, E Farchi, O Raz… - Theory and Practice of …, 2024‏ - Springer
This chapter discusses the concepts of populations and samples of observational units and
the idea of drift detection as being an inference that drift has occurred in a population …

A Framework Analysis for Alternating Components and Drift

S Ackerman, G Barash, E Farchi, O Raz… - Theory and Practice of …, 2024‏ - Springer
This chapter discusses a framework architecture that helps choose the best design of an ML
system based on the data and models that compose the system. As data and business goals …

Principles of Drift Detection and ML Solution Retraining

S Ackerman, G Barash, E Farchi, O Raz… - Theory and Practice of …, 2024‏ - Springer
This chapter introduces the concept of drift as a change in the statistical distributions of
observed data or in the performance of an ML model. Several representative types of drifts …

Testing Solutions Based on Large Language Models

S Ackerman, G Barash, E Farchi, O Raz… - Theory and Practice of …, 2024‏ - Springer
Large language models (LLMs) are ML models trained on extensive data corpora, enabling
them to perform multiple downstream ML tasks. Consequently, using LLMs allows the ML …

Drift in Characterizations of Data

S Ackerman, G Barash, E Farchi, O Raz… - Theory and Practice of …, 2024‏ - Springer
This chapter presents several examples from the authors' research on applications of drift
detection in industrial settings. These include representing a dataset as “slices” based on …

Scientific Analysis of ML Systems

S Ackerman, G Barash, E Farchi, O Raz… - Theory and Practice of …, 2024‏ - Springer
The primary requirement of a good learning system is generalization, ie, the ability to
generate rules that perform well on data similar to the training data. This is achieved through …

Optimal Integration of the ML Solution in the Business Decision Process

S Ackerman, G Barash, E Farchi, O Raz… - Theory and Practice of …, 2024‏ - Springer
The ML system is integrated into a business process to help increase the value obtained
from the process by the organization. Once the probability of error by the ML system is …