Sökning: "Gradient descent method"

Visar resultat 1 - 5 av 16 avhandlingar innehållade orden Gradient descent method.

1. 1. Fuzzy Control for an Unmanned Helicopter

   Författare :Bourhane Kadmiry; Dimiter Driankov; Linköpings universitet; []
   Nyckelord :NATURAL SCIENCES; NATURVETENSKAP; NATURVETENSKAP; NATURAL SCIENCES; Helicopter; Robust control; Fuzzy gain scheduling; Gradient descent method; Computer science; Datavetenskap;

   Sammanfattning : The overall objective of the Wallenberg Laboratory for Information Technology and Autonomous Systems (WITAS) at Linköping University is the development of an intelligent command and control system, containing vision sensors, which supports the operation of a unmanned air vehicle (UAV) in both semi- and full-autonomy modes. One of the UAV platforms of choice is the APID-MK3 unmanned helicopter, by Scandicraft Systems AB. LÄS MER

3. 2. Group-Sparse Regression : With Applications in Spectral Analysis and Audio Signal Processing

   Författare :Ted Kronvall; Statistical Signal Processing Group; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; NATURVETENSKAP; TEKNIK OCH TEKNOLOGIER; NATURAL SCIENCES; ENGINEERING AND TECHNOLOGY; sparse regression; group-sparsity; statistical modeling; regularization; hyperparameter-selection; spectral analysis; audio signal processing; classification; localization; multi-pitch estimation; chroma; convex optimization; ADMM; cyclic coordinate descent; proximal gradient;

   Sammanfattning : This doctorate thesis focuses on sparse regression, a statistical modeling tool for selecting valuable predictors in underdetermined linear models. By imposing different constraints on the structure of the variable vector in the regression problem, one obtains estimates which have sparse supports, i.e. LÄS MER

4. 3. Scalable Optimization Methods for Machine Learning : Acceleration, Adaptivity and Structured Non-Convexity

   Författare :Vien Van Mai; Mikael Johansson; John Duchi; KTH; []
   Nyckelord :ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Large-scale optimization; Anderson acceleration; first-order methods; stochastic optimization; momentum; gradient clipping; Electrical Engineering; Elektro- och systemteknik;

   Sammanfattning : This thesis aims at developing efficient optimization algorithms for solving large-scale machine learning problems. To cope with the increasing scale and complexity of such models, we focus on first-order and stochastic methods in which updates are carried out using only (noisy) information about function values and (sub)gradients. LÄS MER

5. 4. Asynchronous Algorithms for Large-Scale Optimization : Analysis and Implementation

   Författare :Arda Aytekin; Mikael Johansson; Panagiotis K. Patrinos; KTH; []
   Nyckelord :ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; convex optimization; optimization; asynchronous algorithms; algorithms; parallel algorithms; large-scale; big data; Electrical Engineering; Elektro- och systemteknik;

   Sammanfattning : This thesis proposes and analyzes several first-order methods for convex optimization, designed for parallel implementation in shared and distributed memory architectures. The theoretical focus is on designing algorithms that can run asynchronously, allowing computing nodes to execute their tasks with stale information without jeopardizing convergence to the optimal solution. LÄS MER

7. 5. Accelerating Convergence of Large-scale Optimization Algorithms

   Författare :Euhanna Ghadimi; Mikael Johansson; Angelia Nedich; KTH; []
   Nyckelord :ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Convex optimization; Large-scale systems; First-order methods; Convergence analysis; ADMM; Optimization algorithms; Electrical Engineering; Elektro- och systemteknik; Matematik; Mathematics;

   Sammanfattning : Several recent engineering applications in multi-agent systems, communication networks, and machine learning deal with decision problems that can be formulated as optimization problems. For many of these problems, new constraints limit the usefulness of traditional optimization algorithms. LÄS MER