Analysing Neural Network Topologies: a Game Theoretic Approach

Stier, Julian; Gianini, G.; Ziegler, Konstantin

doi:10.1016/j.procs.2018.07.257

Cited by 21 publications

(15 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, biology and structural searches such as e.g. pruning suggest to develop sparse neural network structures [24].…”

Section: Introductionmentioning

confidence: 99%

Structural Analysis of Sparse Neural Networks

Stier

2019

Procedia Computer Science

Self Cite

View full text Add to dashboard Cite

Sparse Neural Networks regained attention due to their potential of mathematical and computational advantages. We give motivation to study Artificial Neural Networks (ANNs) from a network science perspective, provide a technique to embed arbitrary Directed Acyclic Graphs into ANNs and report study results on predicting the performance of image classifiers based on the structural properties of the networks' underlying graph. Results could further progress neuroevolution and add explanations for the success of distinct architectures from a structural perspective.

show abstract

“…Thus, biology and structural searches such as e.g. pruning suggest to develop sparse neural network structures [24].…”

Section: Introductionmentioning

confidence: 99%

Structural Analysis of Sparse Neural Networks

Stier

2019

Procedia Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…Therefore, heuristics [59], predictors [30], and estimators [28,60] are used and are under development to solve this issue. Interestingly, Shapley value has found a unique spot in the field of explainable machine learning [61] and is used to understand deeper and more complicated neural network architectures [61], prune the unnecessary elements [62], and even correct biased networks [60].…”

Section: Discussionmentioning

confidence: 99%

Systematic Perturbation of an Artificial Neural Network:A Step Towards Quantifying Causal Contributions in The Brain

Fakhar

Hilgetag

2021

Preprint

View full text Add to dashboard Cite

Lesion inference analysis is a fundamental approach for characterizing the causal contributions of neural elements to brain function. Historically, it has helped to localize specialized functions in the brain after brain damage, and it has gained new prominence through the arrival of modern optogenetic perturbation techniques that allow probing the functional contributions of neural circuit elements at unprecedented levels of detail.While inferences drawn from brain lesions are conceptually powerful, they face methodological difficulties due to the brain’s complexity. Particularly, they are challenged to disentangle the functional contributions of individual neural elements because many elements may contribute to a particular function, and these elements may be interacting anatomically as well as functionally. Therefore, studies of real-world data, as in clinical lesion studies, are not suitable for establishing the reliability of lesion approaches due to an unknown, potentially complex ground truth. Instead, ground truth studies of well-characterized artificial systems are required.Here, we systematically and exhaustively lesioned a small Artificial Neural Network (ANN) playing a classic arcade game. We determined the functional contributions of all nodes and links, contrasting results from single-element perturbations and perturbing multiple elements simultaneously. Moreover, we computed pairwise causal functional interactions between the network elements, and looked deeper into the system’s inner workings, proposing a mechanistic explanation for the effects of lesions.We found that not every perturbation necessarily reveals causation, as lesioning elements, one at a time, produced biased results. By contrast, multi-site lesion analysis captured crucial details that were missed by single-site lesions. We conclude that even small and seemingly simple ANNs show surprising complexity that needs to be understood for deriving a causal picture of the system. In the context of rapidly evolving multivariate brain-mapping approaches and inference methods, we advocate using in-silico experiments and ground-truth models to verify fundamental assumptions, technical limitations, and the scope of possible interpretations of these methods.Author summaryThe motto “No causation without manipulation” is canonical to scientific endeavors. In particular, neuroscience seeks to find which brain elements are causally involved in cognition and behavior of interest by perturbing them. However, due to complex interactions among those elements, this goal has remained challenging.In this paper, we used an Artificial Neural Network as a ground-truth model to compare the inferential capacities of lesioning the system one element at a time against sampling from the set of all possible combinations of lesions.We argue for employing more exhaustive perturbation regimes since, as we show, lesioning one element at a time provides misleading results. We further advocate using simulated experiments and ground-truth models to verify the assumptions and limitations of brain-mapping methods.

show abstract

“…The number of hidden layers, the activation functions, and the number of neurons per layer are the main parameters of a neural network and must be defined before starting the training [ 54 ], but despite the fact that there have been great advances in this field [ 76 , 77 ], there is no formal method to optimize them [ 9 ].…”

Section: Methodsmentioning

confidence: 99%

Prediction of Mechanical Properties by Artificial Neural Networks to Characterize the Plastic Behavior of Aluminum Alloys

2020

View full text Add to dashboard Cite

In metal forming, the plastic behavior of metallic alloys is directly related to their formability, and it has been traditionally characterized by simplified models of the flow curves, especially in the analysis by finite element simulation and analytical methods. Tools based on artificial neural networks have shown high potential for predicting the behavior and properties of industrial components. Aluminum alloys are among the most broadly used materials in challenging industries such as aerospace, automotive, or food packaging. In this study, a computer-aided tool is developed to predict two of the most useful mechanical properties of metallic materials to characterize the plastic behavior, yield strength and ultimate tensile strength. These prognostics are based on the alloy chemical composition, tempers, and Brinell hardness. In this study, a material database is employed to train an artificial neural network that is able to make predictions with a confidence greater than 95%. It is also shown that this methodology achieves a performance similar to that of empirical equations developed expressly for a specific material, but it provides greater generality since it can approximate the properties of any aluminum alloy. The methodology is based on the usage of artificial neural networks supported by a big data collection about the properties of thousands of commercial materials. Thus, the input data go above 2000 entries. When the relevant information has been collected and organized, an artificial neural network is defined, and after the training, the artificial intelligence is able to make predictions about the material properties with an average confidence greater than 95%.

show abstract

Analysing Neural Network Topologies: a Game Theoretic Approach

Cited by 21 publications

References 16 publications

Structural Analysis of Sparse Neural Networks

Structural Analysis of Sparse Neural Networks

Systematic Perturbation of an Artificial Neural Network:A Step Towards Quantifying Causal Contributions in The Brain

Prediction of Mechanical Properties by Artificial Neural Networks to Characterize the Plastic Behavior of Aluminum Alloys

Contact Info

Product

Resources

About