Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 329 for “"CONVOLUTIONS"”.
-
Generalizations of arithmetic convolutions
NOT AVAILABLE
-
CONVOLUTIONS AND FACTORIZATION THEOREMS
Abstract not available
-
BIONIC: Biological Network Integration using Convolutions
… BIONIC (Biological Network Integration using Convolutions), learns features which contain substantially more functional information compared to existing approaches. BIONIC has unsupervised and semi-supervised learning modes, making use of available gene function annotations. BIONIC is scalable …
-
Graph Convolutions For Teams Of Robots
… where the policies are parametrized by graph convolutions. Additionally, we also develop new methodologies to train these policies and derive technical insights into their behaviors. Building upon these, we design perception action loops for teams of robots that rely only on noisy visual …
-
Vectorizing FFT for faster AI Convolutions
… this thesis we implemented and investigated FFT convolutions that leverage vector length agnostic programming for convolutional neural networks with the ARM Scalable Vector Extension (SVE) and RISC-V ”V” vector extensions. Our research aimed to address the limitations of traditional vectorisation …
-
SYMMETRIZATIONS AND CONVOLUTIONS OF CONVEX BODIES
ΜΕΛΕΤΑΜΕ ΦΑΙΝΟΜΕΝΑ ΥΨΗΛΗΣ ΔΙΑΣΤΑΣΗΣ (ΣΤΟΝ R^N ΓΙΑ N "ΜΕΓΑΛΟ"). Η ΣΥΓΚΕΝΤΡΩΣΗ ΜΕΤΡΟΥ ΑΠΟΤΕΛΕΙ ΘΕΜΕΛΙΩΔΕΣ ΦΑΙΝΟΜΕΝΟ ΣΤΟΝ R^N ΑΛΛΑ ΚΑΙ ΕΡΓΑΛΕΙΟ ΜΕΛΕΤΗΣ. ΑΠΟΔΕΙΚΝΥΟΥΜΕ ΟΤΙ ΣΧΕΤΙΚΑ ΛΙΓΕΣ ΣΥΜΜΕΤΡΙΚΟΠΟΙΗΣΕΙΣ SCHWARZ (ΑΛΛΑ ΚΑΙ ΕΝΔΙΑΜΕΣΕΣ ΤΩΝSCHWARZ ΚΑΙ STEINER ΣΥΜΜΕΤΡΙΚΟΠΟΙΗΣΕΩΝ) ΑΡΚΟΥΝ ΓΙΑ ΝΑ …
-
A Class of Univalent Convolutions of Harmonic Mappings
A planar harmonic mapping is a complex-valued function ƒ : D → C of the form ƒ(x+iy) = u(x,y) + iv(x,y), where u and v are both real harmonic. Such a function can be written as ƒ = h+g where h and g are both analytic; the function w = g'/h' is called the dilatation of ƒ. This thesis considers the …
-
Auto-tuning RISC-V Vectorized convolutions in oneDNN
Convolutional Neural Networks are an essential part in deep learning tasks such as image recognition and object detection. The open-source RISC-V ISA with its vector extension offers a great opportunity for optimizing convolution algorithms on high-performance systems. The objective of this thesis …
-
Discrete time convolutions and elements of Markov renewal theory
Σε αυτή τη διπλωματική παρουσιάζεται μία αλγεβρική προσέγγιση στις συνελίξεις πραγματικών και πινακικών συναρτήσεων σε διακριτό χρόνο. Εξετάζονται οι ιδιότητες τους με τη βοήθεια αλγεβρικών δομών, όπως είναι ο δακτύλιος και η ομάδα. Η χρήση αυτών των αλγεβρικών θεωριών βοηθούν στη συνέχεια της …
-
Convolutions Goss L-Series and Tensor Products of Drinfeld Modules
We present special value results of convolutions of Goss and Pellarin L-series attached to Drinfeld modules that take values in Tate algebras by Papanikolas and the author. Following the same framework, we establish special value results of convolutions of two Goss L-series attached to Drinfeld …
-
Convolutions and Convex Combinations of Harmonic Mappings of the Disk
Let f_1, f_2 be univalent harmonic mappings of some planar domain D into the complex plane C. This thesis contains results concerning conditions under which the convolution f_1 ∗ f_2 or the convex combination tf_1 + (1 − t)f_2 is univalent. This is a long-standing problem, and I provide several …
-
Convolutions: Writing the Mind and the Neurology of the Literary Brain
… of the brain are sometimes termed the cerebral convolutions. But it is a loop in another sense, in the way stories or narratives are often referred to as convolutions (or convoluted) if their plots and themes are complex and resist any linear, straightforward reading. These senses are well …
-
Efficient and Effective Object Detection and Recognition: from Convolutions to Transformers
With the development of Convolutional Neural Networks (CNNs), computer vision has entered a new era, significantly enhancing the performance of tasks such as image classification, object detection, segmentation, and recognition. Furthermore, the introduction of Transformer architectures has brought …
-
On Laplace transforms, generalized gamma convolutions, and their applications in risk aggregation
… and an introduction on Generalized Gamma Convolutions (GGCs). The heart of this dissertation is the final three chapters comprised of three contributions to the literature. In Chapter 3, we study the analytical properties of the Laplace transform of the log-normal distribution. Two …
-
Leveraging Models to Improve Data Efficiency: Navigation, Reinforcement Learning, and Lie Group Convolutions
… worlds, reinforcement learning, and Lie group convolutions. First, consider the problem of navigating to the minimum of a convex potential when there are ellipsoidal obstacles along the way. In particular, we look at the system where the agent estimates its location using local information …
-
Set Images and Convexity Properties of Convolutions for Sum Sets and Difference Sets
… such as almost-periodicity results regarding convolutions. This thesis will focus on the properties of convolutions. Given an abelian group $G$ and sets $A \subseteq G,$ we study the properties of the convolution for sum sets and difference sets, $1_A*1_A$ and $1_A*1_{-A}.$ Given $\bm{x} \in …
-
Optimizing Convolutions in State-of-the-art Convolutional Neural Networks on Intel Xeon Phi
Convolution layers are the core of Convolutional Neural Networks (CNNs), a class of Deep Neural Networks which provide state-of-the-art results in pattern recognition tasks in various domains, such as image recognition, speech recognition, and natural language processing. However, CNNs are very …
-
Accounting for Uncertainty in Process Optimization Initiatives with Statistical Convolutions and Stochastic Programming Techniques
… leading to process improvement. Second, convolutions of normal random variables are explored. Convolutions often arise in engineering problems, and the probability densities of the sums of these random variables are known in the literature. There are practical situations where …
Page 1 of 17