Artificial neural networks (ANNs) are important building blocks in technical applications. They rely on noiseless continuous signals in stark contrast to the discrete action potentials stochastically exchanged among the neurons in real brains. We propose to bridge this gap with Spike-by-Spike (SbS) networks which represent a compromise between non-spiking and spiking versions of generative models. […]

Automatic segmentation of brain tumors from medical images is important for clinical assessment and treatment planning of brain tumors. Recent years have seen an increasing use of convolutional neural networks (CNNs) for this task, but most of them use either 2D networks with relatively low memory requirement while ignoring 3D context, or 3D networks exploiting […]

Abstract If someone unintentionally breaks the rules, do they break the rules? In the abstract, the answer is obviously “yes.” But, surprisingly, when considering specific examples of unintentional, blameless rule‐breaking, approximately half of people judge that no rule was broken. This effect, known as excuse validation, has previously been observed in American adults. Outstanding questions […]