What is a graph and how is it represented for neural networks (adjacency matrix, edge list)?
Machine Learning / AI
What is LambdaRank?
What is unsupervised learning and what models are used?
What is differential privacy and DP-SGD?
What is the difference between gradient boosting and random forest?
How to add a new data source with a short history to logistic regression?
How does p-value relate observed data to the null hypothesis?
What are parametric and non-parametric statistical tests?
How to organize a control group (mock) in risk models?
What is gradient boosting?
How to evaluate the quality of a model using ROC AUC and what do good and bad scores mean?
What is an autoencoder for anomaly detection and how to calculate reconstruction error?
What is RoPE (rotary positional embeddings) and what are its advantages?
How to avoid sampling bias when training a model on approved credits?
What is GCN (Graph Convolutional Network) and its update formula?
What is pivoted normalization?
What metrics are used for regression?
What is pairwise preference and how to calculate it?
What is FSDP (Fully Sharded Data Parallel)?
What is Twyman's law and how to oppose it?