Recursive attention function and loss function change. حسب Wang Linfeng (17102068)

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

"…In doing so we use examples which enable the two approaches to be compared (small, given the computational power required for estimations of algorithmic complexity). 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 حسب Santiago Hernández-Orozco (5070209)

"…In doing so we use examples which enable the two approaches to be compared (small, given the computational power required for estimations of algorithmic complexity). 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 حسب Santiago Hernández-Orozco (5070209)

"…In doing so we use examples which enable the two approaches to be compared (small, given the computational power required for estimations of algorithmic complexity). 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 حسب Santiago Hernández-Orozco (5070209)

"…In doing so we use examples which enable the two approaches to be compared (small, given the computational power required for estimations of algorithmic complexity). 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.…"

Comparison of predictive performance of machine learning algorithms on classifying genes as pro- or anti-longevity. حسب F. William Townes (3216846)

Test results of the benchmark function, the dimension fixed to one hundred. حسب Rahila Hafiz (18137254)

Bayes estimator and posterior risk under different loss functions. حسب Wanting Wang (8612121)

Run times of two algorithms. حسب Gourab Saha (8987405)

الموضوعات:

Friedman ranks of tested methods on CEC2019 benchmark functions. حسب Nebojsa Bacanin (13932723)

LOTUS: A single- and multitask machine learning algorithm for the prediction of cancer driver genes حسب Olivier Collier (7444844)

Features of 13 pSRGs obtained by machine learning methods. حسب Xihao Shen (20347942)

الموضوعات:

Equivalence of loss functions and effects of regularization. حسب Jonathan Vacher (17041542)

الموضوعات: "…produced successful algorithms…"

Best part-machine incidence matrix. حسب Dhulfiqar Hakeem Dhayef (17729684)

الموضوعات:

Convergence curves of the IMGO and comparison algorithms on functions <i>f</i>1−<i>f</i>7. حسب Ying Li (38224)

Table_2_Optimizing functional near-infrared spectroscopy (fNIRS) channels for schizophrenic identification during a verbal fluency task using metaheuristic algorithms.XLSX حسب Dong Xia (54339)

الموضوعات:

Table_1_Optimizing functional near-infrared spectroscopy (fNIRS) channels for schizophrenic identification during a verbal fluency task using metaheuristic algorithms.XLSX حسب Dong Xia (54339)

الموضوعات:

Original data for the study "<b>Improving basin-wide flood estimation from a global hydrological model through spatiotemporal-pattern-</b><b>based </b><b>machine learning</b>" حسب Jiaqing Wang (18814630)

Parameter settings of IWOA and other selected algorithms. حسب Wei Liu (20030)

الموضوعات:

Logarithmic mean convergence curves of different algorithms. حسب Wei Liu (20030)

الموضوعات: