Artificial Intelligence

ai.md

Artificial Intelligence

Mathematics

• Mathematics for Machine Learning

Calculus

Derivatives & gradients Partial derivatives Chain rule Gradient descent

• Essence of Calculus
• Essence of linear algebra
• coursera Math for ML (Linear Algebra, Multivariate Calculus, PCA and Basic ML)
• Multivariable calculus

Linear Algebra

Vectors, matrices, dot product Matrix multiplication Transpose, inverse, determinant Eigenvalues & eigenvectors Singular Value Decomposition (SVD)

• https://www.khanacademy.org/math/linear-algebra

Probability & Statistics

Random variables Mean, variance, expectation Distributions (Normal, Bernoulli, etc.) Bayes theorem Likelihood, entropy

• probability course
• https://www.khanacademy.org/math/statistics-probability

Theory of Computation

• Computability Theory [1 ed.] - S. Barry Cooper

Linear Optimization

Gradient descent Cost/loss functions Convex vs non-convex optimization

• Operations Research [4 ed.] - Wayne L. Winston

Classical ML

Regression classification trees clustering feature engineering. Supervised learning (linear/logistic regression, SVM) Decision trees, random forests Clustering (k-means) Overfitting, regularization Cross-validation, evaluation metrics Feature scaling, encoding

Python (you can keep using Go for backend; ML is mostly in Python) NumPy, pandas, scikit-learn

• https://developers.google.com/machine-learning

• Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow

• Artificial Intelligence A Modern Approach [4 ed. GLOBAL] - Stuart J. Russell, Peter Norvig

• Quick Hands-On

• ML concepts

• Hands-On ML

• Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow (Aurélien Géron) – start with chapters 1–7

• Andrew Ng’s Machine Learning (Coursera) – timeless for intuition

• Machine Learning Algorithms in Depth (Manning)

• Deep Learning with Python (Manning)

• The Hundred-Page Language Models Book

• Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow by Geron Aurelien

• https://www.coursera.org/specializations/machine-learning-introduction

• https://www.coursera.org/specializations/deep-learning

• Algorithms for optimization

• https://ocw.sharif.ir/course/id/545

Deep Learning

Neural networks CNNs RNNs Transformers Feedforward Neural Networks Backpropagation & gradient descent CNNs (images) RNNs / LSTMs (sequences) Transformers (foundation of modern AI) Attention mechanisms

PyTorch (preferred for flexibility) TensorFlow/Keras (for quicker prototyping) Google Colab for free GPU compute

• Dive into Deep Learning (free online book) – https://d2l.ai
• https://ocw.sharif.ir/course/id/532

Generative AI

Diffusion models large language models (LLMs) fine-tuning prompt engineering How GPT-style LLMs are trained (transformer architecture, self-attention) Fine-tuning vs LoRA vs RAG (Retrieval-Augmented Generation) Diffusion models (e.g., Stable Diffusion) Embeddings, tokenization, vector databases (FAISS, Chroma, Pinecone)

• Build a Large Language Model (From Scratch)
• https://github.com/omid-moradi/llm-course-with-roadmaps-

Applied AI / Agents

Building AI systems that use models to reason, act, plan, and interact with tools and APIs. LangChain or LlamaIndex (Python) Agent frameworks (e.g., OpenAI’s Assistants API, CrewAI, AutoGen) Memory, context windows, tool-use Integration with your backend (Go service calling AI microservices) Vector stores and RAG optimization

• https://cloud.google.com/discover/what-are-ai-agents
• AI Agents in Action