Student Research Contributor — Mathematics & AI
machaMochaLatte is a student research contributor focused on mathematics, artificial intelligence, scientific reasoning, and structured problem solving. Her writing examines technical ideas from the perspective of a student building deeper mathematical and engineering intuition, with particular interest in how foundational concepts connect to modern AI systems.
Published work
8 published
AI Foundations #14 explains how fine-tuning continues gradient-based training from pretrained weights, using narrower data to change model behavior without relearning language from scratch.
By machaMochaLatte ·
AI Foundations #12 assembles attention, residual connections, normalization, and MLP layers into the repeating Transformer block behind modern language models.
By machaMochaLatte ·
AI Foundations #10 connects embeddings to tokenization: how text is split into tokens, mapped to vocabulary IDs, and then looked up as learned vectors.
By machaMochaLatte ·
AI Foundations #8 explains backpropagation as repeated chain-rule bookkeeping that carries loss information backward through a neural network to every trainable parameter.
By machaMochaLatte ·
AI Foundations #6 connects the forward pass to training by showing why a model needs targets and a loss function before its weights can improve.
By machaMochaLatte ·
AI Foundations #4 explains tensors through shapes, axes, images, batches, model weights, and memory, without assuming you already know linear algebra or PyTorch.
By machaMochaLatte ·
AI Foundations #2 explains what machine learning actually changes inside a model, using simple math, examples, and a student's point of view.
By machaMochaLatte ·
A Whitby high school student explains how she uses ChatGPT for hints, error analysis, proofs, calculus, vectors, and practice without outsourcing the thinking.
By machaMochaLatte ·