Core Machine Learning Definitions: Algorithms and System Design

Core Machine Learning Concepts and Algorithms

Essential Definitions in Machine Learning

  1. Machine Learning: A field of AI where systems learn patterns from data to make predictions or decisions without being explicitly programmed.
  2. Find-Specific Hypothesis Algorithm: A concept learning algorithm that finds the most specific hypothesis consistent with the training examples.
  3. Concept Learning Task: The task of inferring a Boolean-valued function from training examples of inputs and outputs.
  4. Multilayer Network:
Read More

Deep Learning Fundamentals: GANs, Activation Functions, and Advanced RL

Generative Adversarial Networks (GANs)

A deep learning model featuring two competing neural networks (NNs) — the Generator and the Discriminator — designed to create realistic synthetic data.

(Mnemonic: The Generator creates fake data, and the Discriminator identifies it as real or fake.)

GAN Data Flow

Noise → Generator → Fake Data → Discriminator → Real/Fake

Core Components of GANs

  1. Generator: Creates synthetic data, attempting to fool the Discriminator (G).
  2. Discriminator: Evaluates data input,
Read More

Machine Learning Algorithms: Use Cases and Compute Requirements

Machine Learning Algorithm Comparison

AlgorithmTrain or Test DataUse CasesSupervisedPipe?File TypeCPU or GPU
AutoGluon-TabularTraining and (optionally) validationHigh-accuracy tabular prediction achieved through automated ensembling and multi-layer stacking.YNCSVCPU or GPU (single instance only, M5)
BlazingTextTrainText classification for use cases such as sentiment analysis, spam detection, and hashtag prediction.YYText file (one sentence per line with space-separated tokens)CPU or GPU (single instance
Read More

LLM Cheatsheet: Essential Concepts and Architectures

LLM Cheatsheet: Essential Concepts

Everything you need to recall about Large Language Models (LLMs) — summarized on one page.


What is a Large Language Model (LLM)?

A Large Language Model (LLM) is a deep learning model trained on vast amounts of text data to understand, generate, and manipulate human language.

  • Examples: GPT-4, Claude, LLaMA, Gemini, Mistral, Falcon
  • Core Technology: The Transformer Architecture

LLM Core Components

ComponentDescription
TokenizerConverts text into tokens (subwords, words)
Read More

Natural Language Processing Core Concepts and Techniques

Text Preprocessing and Feature Space Reduction

Which of the following text preprocessing steps can reduce the dimensionality of a bag-of-words feature space?

  • A. Converting all text to lowercase
  • B. Removing common stop words (e.g., “the”, “and”, “of”)
  • D. Stemming or lemmatizing words (e.g., “running” → “run”)

Limitations of Bag-of-Words Representation

Which of the following are limitations of the bag-of-words (unigram) text representation?

  • A. It ignores the order of words in the text
Read More

Integrating SQL, Understanding NoSQL, and MongoDB Fundamentals

Database Programming: Integrating SQL with Host Languages

Introduction to SQL Integration

This section covers how SQL is used in host languages like C and Java, utilizing techniques such as Embedded SQL, Dynamic SQL, JDBC, and SQLJ. It demonstrates essential steps like connecting to a database, declaring host variables, retrieving data using cursors, and executing dynamic queries.

Embedded SQL (C Example)

Embedded SQL allows direct integration of SQL statements within a host language program (e.g.,

Read More