An approach that enables large-batch contrastive learning under memory constraints, similar to gradient accumulation.

Introduction to NVTabular, NVIDIA's GPU-accelerated library for tabular data feature engineering and preprocessing.

Introduction to AutoML and hyperparameter optimization using Bayesian Optimization with Gaussian Process Regression.

Week 11 retrospective of Naver Boostcamp AI Tech covering the Relation Extraction competition, model experiments, and leaderboard submissions.

Curated list of reinforcement learning study resources including lectures, books, and blog posts.

Why weight initialization matters in deep learning and why zero initialization should be avoided.

Data visualization concepts: data types, marks, channels, and pre-attentive attributes.

Fundamentals of RNN including sequence data handling, latent autoregressive models, BPTT, and truncated backpropagation.

Mathematical derivation of gradient descent for linear regression, from L2 norm cost functions to SGD.

Gradient descent basics: differentiation, gradient vectors, partial derivatives, and the nabla operator.

Fundamentals of Bayesian statistics covering Bayes' theorem, conditional probability, posterior updating, and causality interpretation.

CNN fundamentals: convolution operations, kernel mechanics, multi-dimensional convolutions, and backpropagation.

Deep learning fundamentals: key components (data, model, loss, optimizer) and a brief history from AlexNet to GPT-3.

Introduction to neural networks covering linear regression, softmax classification, activation functions, and why deep layers are preferred.

Probability theory foundations for machine learning: probability distributions, joint and conditional distributions, Bayes' rule, and expectation.

Foundations of statistical modeling: parametric vs. nonparametric methods, probability distributions, MLE, and log-likelihood.