Primers • AI

Overview

• Here’s a hand-picked selection of articles on AI fundamentals/concepts that cover the entire process of building neural nets to training them to evaluating results.

Model Architecture

• Linear and Logistic Regression
• k-Nearest Neighbors
• Clustering
• Support Vector Machines (SVM)
• Naive Bayes
• Decision Trees and Ensemble Methods
• ML Algorithms Comparative Analysis
• DL Architectures Comparative Analysis
• Neural Architectures
• Encoder vs. Decoder vs. Encoder-Decoder Models
• Generative Adversarial Networks (GANs)
• Diffusion Models
• Graph Neural Networks
• Attention
• Transformers
• Parameter Efficient Fine-Tuning
• Dropout
• Token Sampling Methods
• Separable Convolutions
• Inductive Bias
• Convolutional Neural Networks
• Reinforcement Learning
• Mixture-of-Experts (MoE)
• State Space Models
• FlashAttention
• Model Acceleration

Data Foundations

• Data Sampling
• Data Imbalance
• Data Quality/Filtering
• Standardization vs. Normalization
• Inter-Annotator Agreement
• Learning Paradigms
• Xavier Initialization
• Padding and Packing
• Regularization
• Gradient Descent and Backprop
• Activation Functions
• Loss Functions
• Activation Functions
• Fine-tuning Models
• Splitting Datasets
• Batchnorm
• Double Descent
• Fine-Tuning and Evaluating BERT
• Training Loss > Validation Loss?
• Bias Variance Tradeoff
• Gradient Accumulation and Checkpointing
• Personally Identifiable Information (PII)
• Hypernetworks
• Distributed Training Parallelism
• k-Fold Cross Validation
• Knowledge Graphs

NLP/LLMs/Agents

• Embeddings
• Prompt Engineering
• Context Engineering
• NLP Tasks
• Preprocessing
• Tokenization
• Overview of Large Language Models (LLMs)
• Diffusion LLMs / Discrete Diffusion Models
• Policy/Preference Optimization
• Agents
• Agentic Reinforcement Learning
• Agentic Design Patterns
• Agent Skills
• LLM-as-a-Judge / Autoraters
• Speculative Decoding
• Reinforcement Fine-Tuning
• Machine Translation
• Factuality in LLMs
• Reasoning in LLMs
• Hallucination Detection and Mitigation
• AI Text Detection Techniques
• Named Entity Recognition
• Textual Entailment
• Retrieval Augmented Generation (RAG)
• LLM Context Length Extension
• Document Intelligence
• Code Mixing and Switching
• Large Language Model Ops (LLMOps)

Vision

• Vision Transformer (ViT)
• Receptive Field
• Residual/Skip Connections
• GPT-4o Native Image Generation

Speech

• Speech Processing

Multimodal AI/VLMs

• Overview of Vision-Language Models (VLMs)
• VLM Architectures
• Computer Control

Offline/Online Evaluation

• Evaluation Metrics
• LLM/VLM Benchmarks
• F-Beta Score
• Online (A/B) Testing

MLOps

• Data Drift
• MLOps Tooling
• MLOps Testing

On-Device AI

• Model Compression
• Federated Learning
• Differential Privacy
• On-device Transformers

Project Planning, Scheduling, Execution

• Objectives and Key Results (OKRs)
• RICE Framework
• Gantt Charts
• Project Management

Models

• BERT
• GPT
• CLIP
• Meena
• ChatGPT
• GPT-4
• Llama
• Alpaca
• Gemini
• Toolformer
• Visual ChatGPT
• TaskMatrix.AI
• BigBird
• OpenAI o1
• DeepSeek-R1
• DeepSeek Janus-Pro
• Gemma 3n
• Qwen 3
• Claude 4
• Veo 3
• DeepSeek-V4

Miscellaneous

• Ilya Sutskever’s Top 30
• GPU Architecture
• Debugging Model Training
• ML Runtimes
• Chain Rule
• Bayes’ Theorem
• Probability Calibration
• Multiclass vs. Multilabel Classification
• N-Dimensional Tensor Product
• PyTorch vs. TensorFlow
• Approximate Nearest Neighbors – Similarity Search
• Transferability Estimation
• TensorBoard
• Convolutional Neural Networks for Text Classification
• Relationship between Hidden Markov Models and Naive Bayes
• Maximum Entropy Markov Models
• Conditional Random Fields

Hyperparameters

• Hyperparameter Tuning
• Hyperparameter Logging

Practice

• Interview Questions