ManySpace
Türkçe Sign in Sign up

AI & MLRecommendedAIML-TS-006

Deep Learning for Forecasting

Global neural forecasters across many series, and the evidence on when they beat classical baselines.

Difficulty
4 / 5
Importance
4 / 5
Study time
1–2 h
Kind of work
Mixed

Why it matters

The learner can compare local classical models with global deep forecasters and state conditions under which each should win.

The route to this topic

Route AIML-TS-006
Natural Numbers What Is a Model? Variables & Constants Learning from Data Tasks: Regression, Classification, and Beyond Features and Targets Solving Linear Equations Function Notation & Composition Datasets and Splits Sequences and Order Linear Regression I: Prediction and Residuals Complex Numbers Data Leakage Train, Validation, and Test Errors Loss and Fitting: Squared Error Basic Ratios Unit Circle Offline Evaluation Autoregression Polynomial Functions Regression Metrics Intuitive Limits Continuity Definition of the Derivative Differentiation Rules Chain Rule Antiderivatives & Indefinite Integrals Derivatives of Transcendental Functions Riemann Sums & Definite Integral Fundamental Theorem of Calculus Integration by Parts Sample Spaces & Events Stochastic Processes Basics Time Series Structure: Trend, Seasonality, Stationarity Autoregressive and ARIMA Models Forecast Evaluation and Backtesting Deep Learning for Forecasting