Optimized for Your Hardware
Intel® DAAL is tuned for a broad range of Intel® processors (including Intel Atom®, Intel® Core™, and Intel® Xeon® processors) targeting IoT gateways to back-end servers, since applications may benefit from splitting analytics processing across several platforms.
Optimized for Developer Productivity
Provides advanced Python*, C++, and Java* data analytics functions spanning all processing stages, pre-optimized and ready to use to reduce software development time.
Intel has partnered with the development team from the popular Python analytics library scikit-learn* that provides Intel DAAL accelerations to commonly used routines and algorithms. To get this version of scikit-learn with the Intel® Distribution for Python*, see Get Started.
Analytics at the Edge or in a Cluster Environment
Batch, streaming, and distributed compute models are supported for covering a range of sizes and performance requirements for application data sets. The mathematical routines in Intel DAAL are built from scratch for efficient processing of incremental learning and master-slave distributed workloads. Developers are provided with a unifying API to encompass all of these processing models.
Low Order Moments
Computes the basic dataset characteristics such as sums, means, second order raw moments, variances, standard deviations, etc.
Computes quantiles that summarize the distribution of data across equal-sized groups as defined by quantile orders.
Correlation and Variance-Covariance Matrices
Quantifies pairwise statistical relationship between feature vectors.
Cosine Distance Matrix
Measures pairwise similarity between feature vectors using cosine distances.
Correlation Distance Matrix
Measures pairwise similarity between feature vectors using correlation distances.
Decomposes a symmetric positive-definite matrix into a product of a lower triangular matrix and its transpose. This decomposition is a basic operation used in solving linear systems, nonlinear optimization, Kalman filtration, etc.
Decomposes a general matrix into a product of an orthogonal matrix and an upper triangular matrix. This decomposition is used in solving linear inverse and least squares problems. It is also a fundamental operation in finding eigenvalues and eigenvectors.
Singular Value Decomposition (SVD)
Decomposes a matrix into a product of a left singular vector, singular values, and a right singular vector. It is the basis of principal component analysis (PCA), solving linear inverse problems, and data fitting.
Principal Component Analysis (PCA)
Reduces the dimensionality of data by transforming input feature vectors into a new set of principal components that are orthogonal to each other.
Partitions a dataset into clusters of similar data points. Each cluster is represented by a centroid, which is the mean of all data points in the cluster.
Finds maximum-likelihood estimate of the parameters in models. It is used for the Gaussian Mixture Model as a clustering method. It can also be used in non-linear dimensionality reduction, missing value problems, etc.
Identifies observations that are abnormally distant from other observations. An entire feature vector (multivariate) or a single feature value (univariate), can be considered in determining if the corresponding observation is an outlier.
Discovers a relationship between variables with certain level of confidence.
Linear and Radial Basis Function Kernel Functions
Map data onto higher-dimensional space.
Compute a set of numeric values to characterize quantitative properties of the results returned by analytical algorithms. These metrics include a confusion matrix, accuracy, precision, recall, F-score, etc.
Neural Networks for Deep Learning
A programming paradigm that enables a computer to learn from observational data.
Logistic, Linear, and Ridge Regressions
Models relationship between dependent variables and one or more explanatory variables by fitting linear equations to observed data.
Naïve Bayes Classifier
Splits observations into distinct classes by assigning labels. Naïve Bayes is a probabilistic classifier that assumes independence between features. Often used in text classification and medical diagnosis, it works well even when there is some level of dependence between features.
Builds a strong classifier from an ensemble of weighted weak classifiers, by iteratively re-weighting according to the accuracy measured for the weak classifiers. A decision stump is provided as a weak classifier. Available boosting algorithms include AdaBoost (a binary classifier), BrownBoost (a binary classifier), and LogitBoost (a multi-class classifier).
Support Vector Machine (SVM)
SVM is a popular binary classifier. It computes a hyperplane that separates observed feature vectors into two classes.
Builds a multiclass classifier using a binary classifier such as SVM.
Alternating Linear Squares (ALS)
Collaborative filtering method of making predictions about the preferences of a user, based on preference information collected from many users.
A method commonly used in data mining. The goal is to create a model that predicts the value of a target variable based on several input variables that use a decision tree as a predictive model, to go from observations about an item (represented in the branches) to conclusions about the item's target value (represented in the leaves).
An ensemble learning method for classification, regression and other tasks, which operate by constructing a multitude of decision trees at training time and outputting the mode of the classes (classification), or mean prediction (regression) of the individual trees.