Eikosstatistics & data science

Machine Learning & Artificial Intelligence · Artificial Intelligence & Deep Learning

Implementation, Deployment, and Maintenance of AI Models · Advanced Engineering Manual

Public introduction · full guide in Eikos

Introduction

What this guide covers

Introduction Production Systems and Artificial Intelligence

Overview

Topics covered

  • Introduction
  • Implementation, Deployment and Maintenance of AI Models
  • The lifecycle of machine learning in production
  • The Discrepancy between Training and Serving (Training-Serving Skew)
  • Serialization and portability of models
  • Portability Standards: The ONNX ecosystem

Related concepts

Main connections

  • Calculus & differentiation
  • Variance & standard deviation
  • Data drift & concept shift
  • Bayes' theorem & priors
  • Neural networks & deep learning
  • Hypothesis testing

Compatible notation

Mathematical sample in LaTeX

The expression is rendered accessibly, with its LaTeX source preserved below.

Y=ReLU(γ(W*X+b−μσ2+ϵ)+β)⟹Y=Kernel_Fusion(X,W^,b^)
View LaTeX sourceY = \text{ReLU}\left( \gamma \left( \frac{W * X + b - \mu}{\sqrt{\sigma^2 + \epsilon}} \right) + \beta \right) \quad\Longrightarrow\quad Y = \mathbf{Kernel\_Fusion}(X, \hat{W}, \hat{b})