Attack and defense behaviors between a single predator and a single prey using the sensory–motor algorithm. by Hiroyuki Ichijo (13891153)

3D modeling qualities of the AS single-template models built by including DOPE in the objective function of MODELLER. by Giacomo Janson (8138517)

Results of searching performance of the improved NAG algorithm on Sphere function and Griewank function. by Rui Zhang (13940)

PSNR (dB) and SSIM of the deblurred images, and the algorithms’ running time (in seconds) on VOC2012 database. by Wei Zhou (24328)

A comparison between the static Python-based visualizations of the p65 activity in activated fibroblasts and the dynamic, HTML-based visualizations that use these same reduction me... by Hector Torres (11708207)

Principal component analysis (PCA) of sub-layer mean intensities. by Maëlle Vilbert (17101954)

3D modeling qualities of the AM multiple-template models built by including DOPE in the objective function of MODELLER. by Giacomo Janson (8138517)

datasheet1_Algorithmic Probability-Guided Machine Learning on Non-Differentiable Spaces.pdf by Santiago Hernández-Orozco (5070209)

“…We find and report that 1) machine learning can successfully be performed on a non-smooth surface using algorithmic complexity; 2) that solutions can be found using an algorithmic-probability classifier, establishing a bridge between a fundamentally discrete theory of computability and a fundamentally continuous mathematical theory of optimization methods; 3) a formulation of an algorithmically directed search technique in non-smooth manifolds can be defined and conducted; 4) exploitation techniques and numerical methods for algorithmic search to navigate these discrete non-differentiable spaces can be performed; in application of the (a) identification of generative rules from data observations; (b) solutions to image classification problems more resilient against pixel attacks compared to neural networks; (c) identification of equation parameters from a small data-set in the presence of noise in continuous ODE system problem, (d) classification of Boolean NK networks by (1) network topology, (2) underlying Boolean function, and (3) number of incoming edges.…”

datasheet2_Algorithmic Probability-Guided Machine Learning on Non-Differentiable Spaces.zip by Santiago Hernández-Orozco (5070209)

“…We find and report that 1) machine learning can successfully be performed on a non-smooth surface using algorithmic complexity; 2) that solutions can be found using an algorithmic-probability classifier, establishing a bridge between a fundamentally discrete theory of computability and a fundamentally continuous mathematical theory of optimization methods; 3) a formulation of an algorithmically directed search technique in non-smooth manifolds can be defined and conducted; 4) exploitation techniques and numerical methods for algorithmic search to navigate these discrete non-differentiable spaces can be performed; in application of the (a) identification of generative rules from data observations; (b) solutions to image classification problems more resilient against pixel attacks compared to neural networks; (c) identification of equation parameters from a small data-set in the presence of noise in continuous ODE system problem, (d) classification of Boolean NK networks by (1) network topology, (2) underlying Boolean function, and (3) number of incoming edges.…”

datasheet1_Algorithmic Probability-Guided Machine Learning on Non-Differentiable Spaces.pdf by Santiago Hernández-Orozco (5070209)

“…We find and report that 1) machine learning can successfully be performed on a non-smooth surface using algorithmic complexity; 2) that solutions can be found using an algorithmic-probability classifier, establishing a bridge between a fundamentally discrete theory of computability and a fundamentally continuous mathematical theory of optimization methods; 3) a formulation of an algorithmically directed search technique in non-smooth manifolds can be defined and conducted; 4) exploitation techniques and numerical methods for algorithmic search to navigate these discrete non-differentiable spaces can be performed; in application of the (a) identification of generative rules from data observations; (b) solutions to image classification problems more resilient against pixel attacks compared to neural networks; (c) identification of equation parameters from a small data-set in the presence of noise in continuous ODE system problem, (d) classification of Boolean NK networks by (1) network topology, (2) underlying Boolean function, and (3) number of incoming edges.…”

datasheet2_Algorithmic Probability-Guided Machine Learning on Non-Differentiable Spaces.zip by Santiago Hernández-Orozco (5070209)

“…We find and report that 1) machine learning can successfully be performed on a non-smooth surface using algorithmic complexity; 2) that solutions can be found using an algorithmic-probability classifier, establishing a bridge between a fundamentally discrete theory of computability and a fundamentally continuous mathematical theory of optimization methods; 3) a formulation of an algorithmically directed search technique in non-smooth manifolds can be defined and conducted; 4) exploitation techniques and numerical methods for algorithmic search to navigate these discrete non-differentiable spaces can be performed; in application of the (a) identification of generative rules from data observations; (b) solutions to image classification problems more resilient against pixel attacks compared to neural networks; (c) identification of equation parameters from a small data-set in the presence of noise in continuous ODE system problem, (d) classification of Boolean NK networks by (1) network topology, (2) underlying Boolean function, and (3) number of incoming edges.…”

Fig 1 - by Yuh-Chin T. Huang (17867207)

Reconstructing <i>sparse</i>, binary patterns using message passing algorithms and PCA. by Sebastian Goldt (14522594)

“…Lines depict the result of the state evolution, while crosses denote the performance of the AMP algorithm on an instance of the problem. While AMP performs the same starting from both initialisations for <i>ρ</i> = 0.1 and <i>ρ</i> = 0.3, there is a gap in performance for <i>ρ</i> = 0.05, which might hint at the existence of a hard phase (see main text). …”

Information of nodes and pipes of NYN. by Yi Tao (178829)

Subjects: “…evolutionary genetic algorithm…”

The topology of the NYN. by Yi Tao (178829)

Subjects: “…evolutionary genetic algorithm…”

The result of Wilcoxon signed-rand test. by Yi Tao (178829)

Subjects: “…evolutionary genetic algorithm…”

The Simulation and optimization process of pipe diameter selection. by Yi Tao (178829)

Subjects: “…evolutionary genetic algorithm…”

Optional pipe diameter and unit price of NYN. by Yi Tao (178829)

Subjects: “…evolutionary genetic algorithm…”

Optional pipe diameter and unit price of HN. by Yi Tao (178829)

Subjects: “…evolutionary genetic algorithm…”

The topology of HN. by Yi Tao (178829)

Subjects: “…evolutionary genetic algorithm…”