Essays about: "plasticitet"
Showing result 1 - 5 of 26 essays containing the word plasticitet.
-
1. Adversarial robustness of STDP-trained spiking neural networks
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Adversarial attacks on machine learning models are designed to elicit the wrong behavior from the model. One such attack on image classifiers are maliciously crafted inputs that, to the human eye, look untampered with but have been carefully altered to cause misclassification. READ MORE
-
2. Regression with Bayesian Confidence Propagating Neural Networks
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Bayesian Confidence Propagating Neural Networks (BCPNNs) are biologically inspired artificial neural networks. These networks have been modeled to account for brain-like aspects such as modular architecture, divisive normalization, sparse connectivity, and Hebbian learning. READ MORE
-
3. Influence from temperature variations in stacking fault energy on the mechanical properties of stainless steels
University essay from KTH/MaterialvetenskapAbstract : This paper investigates the mechanical properties and deformation mechanisms of austenitic stainless steels and how they relate to the material property of stacking fault energy (SFE) and its relation to temperature and nickel content. Austenitic stainless steels are commonly used and well known for good mechanical properties and deformation characteristics. READ MORE
-
4. Volumetric Image Segmentation of Lizard Brains
University essay from KTH/Tillämpad fysikAbstract : Accurate measurement brain region volumes are important in studying brain plasticity, which brings insight into the fundamental mechanisms in animal, memory, cognitive, and behavior research. The traditional methods of brain volume measurements are ellipsoid or histology. READ MORE
-
5. Modelling synaptic rewiring in brain-like neural networks for representation learning
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : This research investigated the concept of a sparsity method inspired by the principles of structural plasticity in the brain in order to create a sparse model of the Bayesian Confidence Propagation Neural Networks (BCPNN) during the training phase. This was done by extending the structural plasticity in the implementation of the BCPNN. READ MORE