Zettelkasten/Terminology Information95 Clustering Information Clustering is a type of unsupervised learning technique used to group together similar objects in a dataset. The goal of clustering is to minimize the intra-cluster distance while maximizing the inter-cluster distance. The most common clustering algorithms include K-Means, Hierarchical, DBSCAN, and Gaussian Mixture Models. K-Means clustering divides the dataset into k distinct groups.. Zettelkasten/Terminology Information 2023. 4. 1. MA (Moving Average) Information MA (Moving Average) is a time series forecasting method that involves calculating the average of past data points over a sliding time window. The size of the window is typically fixed and determines how many past data points to include in the calculation. The goal of MA is to identify patterns or trends in the data that are difficult to observe with raw data. It is a simple and widel.. Zettelkasten/Terminology Information 2023. 3. 31. AI (Artificial Intelligence) Information AI (Artificial Intelligence) is a branch of computer science that focuses on creating intelligent machines that can simulate human intelligence and behavior. It involves using algorithms, mathematical models, and computer programs to enable machines to perform tasks that typically require human intelligence, such as learning, problem-solving, perception, decision making, and natural .. Zettelkasten/Terminology Information 2023. 3. 30. Statistical model Information A statistical model is a mathematical framework used to describe the relationship between a set of variables. It allows us to make inferences about the underlying population by analyzing a sample of data. Statistical models can be used for a wide range of applications, including forecasting, classification, and regression. There are two main types of statistical models: parametric an.. Zettelkasten/Terminology Information 2023. 3. 29. LTLF (Long-Term Load Forecasting) Information LTLF (Long-Term Load Forecasting) is a type of load forecasting that predicts the energy demand for a period of several years, typically ranging from 5 to 20 years into the future. LTLF models are typically used by utility companies, energy planners, and policy makers to make long-term investment decisions, plan for future capacity requirements, and ensure energy security and reliabi.. Zettelkasten/Terminology Information 2023. 3. 27. MTLF (Mid-Term Load Forecasting) Information MTLF (Mid-Term Load Forecasting) is a type of load forecasting used to predict energy consumption and demand over an intermediate period of time, typically ranging from a few days to several weeks. MTLF is generally used by power utilities and energy companies to better plan their energy generation, transmission, and distribution activities, optimize energy production, and improve gr.. Zettelkasten/Terminology Information 2023. 3. 27. VSTLF (Very Short-Term Load Forecasting) Information Very Short-Term Load Forecasting (VSTLF) is a type of load forecasting that predicts the power consumption of an electrical grid for a few minutes up to a few hours ahead of time, typically up to 24 hours in advance. The forecasting is based on the assumption that the load is influenced by factors such as weather, time of day, day of the week, and special events. VSTLF plays a vital .. Zettelkasten/Terminology Information 2023. 3. 26. Min-Max scaling Information Min-Max scaling is a technique used to scale numerical features to a fixed range of [0, 1]. It is a linear scaling method that linearly transforms each feature to the specified range. The formula used for Min-Max scaling is: X_scaled = (X - X_min) / (X_max - X_min) where X_scaled is the scaled feature value, X is the original feature value, X_min is the minimum value of the feature, .. Zettelkasten/Terminology Information 2023. 3. 25. Adam (Adaptive Moment Estimation) Information Adam (Adaptive Moment Estimation) is a stochastic gradient descent optimization algorithm commonly used for training deep neural networks. It is an adaptive learning rate optimization algorithm that combines the advantages of both AdaGrad and RMSProp optimizers. The algorithm maintains an exponentially decaying average of past gradients and past squared gradients to compute the adapt.. Zettelkasten/Terminology Information 2023. 3. 24. ANN (Artificial Neural Network) Information An ANN (Artificial Neural Network) is a machine learning model that is inspired by the structure and function of the human brain and nervous system. ANN consists of interconnected processing nodes (neurons) that are arranged in layers (input, hidden, and output) to process information and perform a variety of tasks, such as classification, regression, and prediction. Each neuron in a.. Zettelkasten/Terminology Information 2023. 3. 23. KNN (K-Nearest Neighbors) Information KNN (K-Nearest Neighbors) is a type of machine learning algorithm used for classification and regression. It's a non-parametric algorithm, which means it doesn't make any assumptions about the underlying data distribution. The algorithm works by finding the K number of nearest data points to a given data point based on a similarity metric, usually Euclidean distance. The value of K i.. Zettelkasten/Terminology Information 2023. 3. 22. ARX (AutoRegressive with eXogenous inputs) Information ARX (AutoRegressive with eXogenous inputs) is a linear model used in time-series analysis and forecasting, where the output variable (Y) is modeled as a function of its own lagged values (AR term) and the lagged values of one or more exogenous input variables (X term). The ARX model is a combination of an AR model and an external input, making it a more general class of models compar.. Zettelkasten/Terminology Information 2023. 3. 21. OE (Output Error) Information The OE (Output Error) model is a type of linear dynamic model that is commonly used in system identification and control theory. The model is based on the idea that the output of a system is a function of its input and past outputs, as well as any external disturbances that may be present. The model is expressed in terms of a transfer function that relates the input to the output, as.. Zettelkasten/Terminology Information 2023. 3. 20. Cold-start problem Information The cold-start problem is a challenge in recommendation systems where there is not enough data about a new user or item to make accurate predictions. It arises when there are no historical interactions or preferences available for a user or item, or when the available data is sparse or unreliable. The cold-start problem can occur for new users who have just joined the platform or for.. Zettelkasten/Terminology Information 2023. 3. 20. ARMAX (AutoRegressive Moving Average model with eXogenous inputs) Information ARMAX (AutoRegressive Moving Average model with eXogenous inputs) is a type of statistical model that combines autoregressive (AR) and moving average (MA) models with external variables, also known as exogenous variables. The model assumes that the output variable depends on its past values, the past values of the error term, and past values of the exogenous variables. ARMAX models a.. Zettelkasten/Terminology Information 2023. 3. 19. Attention Information Attention mechanisms are widely used in machine learning and natural language processing tasks to help model understand the relative importance of different parts of the input. The attention mechanism works by computing the similarity between a "query" and "key" vectors to determine the importance of the key for the given query. In an attention mechanism, the query vector represents .. Zettelkasten/Terminology Information 2023. 3. 19. CNN-LSTM Information CNN-LSTM is a hybrid deep learning architecture that combines Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks. CNN-LSTM is designed for sequence prediction tasks, where the input is a time-series or spatiotemporal data. In the CNN-LSTM architecture, the CNN layer is used to extract local features from the input sequence, while the LSTM layer captures t.. Zettelkasten/Terminology Information 2023. 3. 18. DA (Domain Adaptation) Information DA (Domain Adaptation) is a subfield of machine learning that aims to adapt models trained on a source domain to perform well on a target domain, where the distributions of the source and target data differ. The primary goal of DA is to improve the generalization of a model to new, unseen data, especially in scenarios where the target data is limited or expensive to collect. There ar.. Zettelkasten/Terminology Information 2023. 3. 18. CNN (Convolutional Neural Network) Information CNN (Convolutional Neural Network) is a type of neural network that has been widely used for image and video processing tasks. CNNs consist of multiple layers that extract and transform features from input data. The core building block of a CNN is the convolutional layer, which applies a set of learnable filters to the input data. The filters convolve across the input data, computing.. Zettelkasten/Terminology Information 2023. 3. 17. NRMSE (Normalized Root Mean Squared Error) Information NRMSE (Normalized Root Mean Squared Error) is a measure of the accuracy of a regression model, representing the ratio of the root mean squared error to the range of the dependent variable. It is used to compare the performance of different models or to evaluate the accuracy of a model over time. The formula for NRMSE is: NRMSE = RMSE / (y_max - y_min), where RMSE is the root mean squ.. Zettelkasten/Terminology Information 2023. 3. 17. 이전 1 2 3 4 5 다음