Implementing a Machine Learning Function Orchestration

We study the predict+optimise problem, where machine learning and combinatorial optimisation must interact to achieve a common goal. These problems are important when optimisation needs to be performed on input parameters that are not fully observed but must instead be estimated using machine learning. Our contributions are two-fold: 1) we provide theoretical insight into the properties and computational complexity of predict+optimise problems in general, and 2) develop a novel framework that, in contrast to related work, guarantees to compute the optimal parameters for a linear learning function given any ranking optimisation problem. We illustrate the applicability of our framework for the particular case of the unit-weighted knapsack predict+optimise problem and evaluate on benchmarks from the literature.

Download Full-text

Structuring Validation Targets of a Machine Learning Function Applied to Automated Driving

Developments in Language Theory - Lecture Notes in Computer Science ◽

10.1007/978-3-319-99130-6_4 ◽

2018 ◽

pp. 45-58 ◽

Cited By ~ 11

Author(s):

Lydia Gauerhof ◽

Peter Munk ◽

Simon Burton

Keyword(s):

Machine Learning ◽

Automated Driving ◽

Learning Function

Download Full-text

Genetic Evolutionary Learning Fitness Function (GELFF) for Feature Diagnosis to Software Fault Prediction

International Journal of Innovative Technology and Exploring Engineering - Special Issue ◽

10.35940/ijitee.k1233.09811s19 ◽

2019 ◽

Vol 8 (11S) ◽

pp. 1151-1161

Keyword(s):

Machine Learning ◽

Feature Selection ◽

Fitness Function ◽

Fault Prediction ◽

Evolutionary Learning ◽

Software Fault Prediction ◽

Underlying Process ◽

Learning Function ◽

Wide Range ◽

Software Fault

Nowadays, proper feature selection f+orFault prediction is very perplexing task. Improper feature selection may lead to bad result. To avoid this, there is a need to find the aridity of software fault. This is achieved by finding the fitness of the evolutionaryAlgorithmic function. In this paper, we finalize the Genetic evolutionarynature of our Feature set with the help of Fitness Function. Feature Selection is the objective of the prediction model tocreate the underlying process of generalized data. The wide range of data like fault dataset, need the better objective function is obtained by feature selection, ranking, elimination and construction. In this paper, we focus on finding the fitness of the machine learning function which is used in the diagnostics of fault in the software for the better classification.

Download Full-text

Fast Linear Interpolation

ACM Journal on Emerging Technologies in Computing Systems ◽

10.1145/3423184 ◽

2021 ◽

Vol 17 (2) ◽

pp. 1-15

Author(s):

Nathan Zhang ◽

Kevin Canini ◽

Sean Silva ◽

Maya Gupta

Keyword(s):

Machine Learning ◽

Piecewise Linear ◽

Lattice Models ◽

Function Class ◽

Linear Interpolation ◽

Linear Functions ◽

Piecewise Linear Functions ◽

Learning Function ◽

Interpolation Operators ◽

New Strategies

We present fast implementations of linear interpolation operators for piecewise linear functions and multi-dimensional look-up tables. These operators are common for efficient transformations in image processing and are the core operations needed for lattice models like deep lattice networks, a popular machine learning function class for interpretable, shape-constrained machine learning. We present new strategies for an efficient compiler-based solution using MLIR to accelerate linear interpolation. For real-world machine-learned multi-layer lattice models that use multidimensional linear interpolation, we show these strategies run 5-10× faster on a standard CPU compared to an optimized C++ interpreter implementation.

Download Full-text

Mind wandering as data augmentation: How mental travel supports abstraction

Behavioral and Brain Sciences ◽

10.1017/s0140525x1900311x ◽

2020 ◽

Vol 43 ◽

Author(s):

Myrthe Faber

Keyword(s):

Machine Learning ◽

Data Augmentation ◽

Mental Content ◽

Mind Wandering ◽

Theoretical Framework ◽

Important Addition

Abstract Gilead et al. state that abstraction supports mental travel, and that mental travel critically relies on abstraction. I propose an important addition to this theoretical framework, namely that mental travel might also support abstraction. Specifically, I argue that spontaneous mental travel (mind wandering), much like data augmentation in machine learning, provides variability in mental content and context necessary for abstraction.

Download Full-text