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.
Design/Architecture
- ML Algorithms Comparative Analysis
- DL Architectures Comparative Analysis
- Linear and Logistic Regression
- Prompt Engineering
- Generative Adversarial Networks (GANs)
- Diffusion Models
- Graph Neural Networks
- Attention
- Separable Convolutions
- Inductive Bias
- Convolutional Neural Networks
- Reinforcement Learning
- Standardization vs. Normalization
- Multiclass vs. Multilabel Classification
- Mixture-of-Experts
- State Space Models
- Agents
- Ensemble Methods and Decision Trees
- Quantization
- Model Acceleration
- Cross Validation
- MLOps Tooling
- MLOps Testing
Training
- Data Sampling
- Learning Paradigms
- Xavier Initialization
- Padding and Packing
- Regularization
- Gradient Descent and Backprop
- Activation Functions
- Loss Functions
- Activation Functions
- Fine-tuning Models
- Splitting Datasets
- Batchnorm
- Dropout
- Double Descent
- Fine-Tuning and Evaluating BERT
- Training Loss > Validation Loss?
- SVM Kernel/Polynomial Trick
- Bias Variance Tradeoff
- Gradient Accumulation and Checkpointing
- Parameter Efficient Fine-Tuning
- Hypernetworks
- Distributed Training Parallelism
Speech
Vision
Models
NLP
- Word Vectors/Embeddings
- NLP Tasks
- Preprocessing
- Tokenization
- Data Sampling
- Neural Architectures
- Attention
- Transformers
- Token Sampling Methods
- Encoder vs. Decoder vs. Encoder-Decoder Models
- Language Models
- Overview of Large Language Models (LLMs)
- Overview of Vision-Language Models (VLMs)
- LLM Alignment
- Machine Translation
- Knowledge Graphs
- Hallucination Mitigation
- AI Text Detection Techniques
- Named Entity Recognition
- Textual Entailment
- Retrieval Augmented Generation (RAG)
- LLM Context Length Extension
- Document Intelligence
- Personalizing Large Language Models
- Code Mixing and Switching
- Large Language Model Ops (LLMOps)
- Convolutional Neural Networks for Text Classification
- Relationship between Hidden Markov Model and Naive Bayes
- Maximum Entropy Markov Models and Logistic Regression
- Conditional Random Fields for Sequence Prediction
- LLM/VLM Benchmarks
Models
Multimodal
Models
Privacy-Preserving/On-Device AI
Evaluation
MLOps/Production
Miscellaneous
- Ilya Sutskever’s Top 30
- Debugging Model Training
- Chain Rule
- Bayes’ Theorem
- Probability Calibration
- N-Dimensional Tensor Product
- PyTorch vs. TensorFlow
- Approximate Nearest Neighbors – Similarity Search
- Transferability Estimation
- TensorBoard
- Project Management