#ml

Cross-validation trains and evaluates a model multiple times on different subsets of data giving a more reliable estimate of generalization performance especially for small datasets. The most common form is…

A feature store is a centralized repository for ML features that solves the training-serving skew problem by ensuring features computed at training time are computed identically at serving time. It…

Precision is the fraction of positive predictions that are actually positive. Recall is the fraction of actual positives that were correctly identified. F1 is their harmonic mean. Which matters depends…

Gradient boosting builds trees sequentially each correcting the errors of the previous. Random Forest builds trees in parallel independently. Gradient boosting typically achieves higher accuracy but is slower to train…

Word embeddings are dense numerical vectors representing words where semantically similar words have similar vectors. Word2Vec trains a neural network to predict surrounding words (skip-gram) or predict a word from…

Feature leakage (data leakage) is when information from the future or from the target variable is included in the training features causing artificially high training metrics that completely fail to…

To fine-tune a language model for a specific task, I would first gather a relevant dataset and preprocess it to fit the model’s input format. Retrieval-augmented generation enhances this by…

Model drift is the degradation of model performance over time as the real-world data distribution changes after deployment. Detect with monitoring (input distribution prediction distribution and ground truth metrics). Handle…

Overfitting is when a model learns the training data too well — including its noise — and performs poorly on new data. Detect it by comparing training and validation accuracy.…

During backpropagation in deep networks gradients shrink exponentially as they propagate backward through many layers making early layers learn very slowly or not at all. Solutions include ReLU activations batch…

Batch GD computes gradients on the entire dataset — slow but stable. Stochastic GD (SGD) computes gradients on one example — fast but noisy. Mini-batch GD computes on a subset…

Supervised learning trains on labeled data (input-output pairs). Unsupervised learning finds patterns in unlabeled data with no predefined outputs.