Eikosstatistics & data science

Machine Learning & Artificial Intelligence · Artificial Intelligence & Deep Learning

Natural Language Processing with Modern Models

Public introduction · full guide in Eikos

Introduction

What this guide covers

Introduction Treatise on Mathematical Engineering and Architecture

Overview

Topics covered

  • Introduction
  • From Probabilistic Models to Vector Space
  • 1.1 N-gram Models and Markov Hypotheses
  • 1.2 Distribution Vector Spaces and Embeddings
  • 1.3 Dense Embeddings Learning Models
  • Recurrent Networks (RNN, LSTM, GRU) and the Limitation of Gradient Vanishing

Related concepts

Main connections

  • Vector embeddings & latent space
  • Linear algebra & matrices
  • Self-attention & Transformer architectures
  • Variance & standard deviation
  • Generative AI & LLM evaluation
  • Logistic regression

Compatible notation

Mathematical sample in LaTeX

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

P(w1,w2,…,wT)=∏t=1TP(wt∣w1,w2,…,wt−1)
View LaTeX sourceP(w_1, w_2, \dots, w_T) = \prod_{t=1}^{T} P(w_t \mid w_1, w_2, \dots, w_{t-1})