No abstract

Complete reconstructions of vertebrate neuronal circuits on the synaptic level require new approaches. Here, serial section transmission electron microscopy was automated to densely reconstruct four volumes, totaling 670μm3, from the rat hippocampus as proving grounds to determine when axo-dendritic proximities predict synapses. First, in contrast with Peters’ rule, the density of axons within reach of dendritic spines did not predict synaptic density along dendrites because the fraction of axons making synapses was variable. Second, an axo-dendritic touch did not predict a synapse; nevertheless, the density of synapses along a hippocampal dendrite appeared to be a universal fraction, 0.2, of the density of touches. Finally, the largest touch between an axonal bouton and spine indicated the site of actual synapses with about 80% precision, but would miss about half of all synapses. Thus, it will be difficult to predict synaptic connectivity using data sets missing ultrastructural details that distinguish between axo-dendritic touches and bona fide synapses.

Neural network models of early sensory processing typically reduce the dimensionality of streaming input data. Such networks learn the principal subspace, in the sense of principal component analysis (PCA), by adjusting synaptic weights according to activity-dependent learning rules. When derived from a principled cost function these rules are nonlocal and hence biologically implausible. At the same time, biologically plausible local rules have been postulated rather than derived from a principled cost function. Here, to bridge this gap, we derive a biologically plausible network for subspace learning on streaming data by minimizing a principled cost function. In a departure from previous work, where cost was quantified by the representation, or reconstruction, error, we adopt a multidimensional scaling (MDS) cost function for streaming data.The resulting algorithm relies only on biologically plausible Hebbian and anti-Hebbian local learning rules. In a stochastic setting, synaptic weights converge to a stationary arXiv:1503.00669v1 [q-bio.NC]

Few-shot learning is a nascent research topic, motivated by the fact that traditional deep learning methods require tremendous amounts of data. The scarcity of annotated data becomes even more challenging in semantic segmentation since pixellevel annotation in segmentation task is more labor-intensive to acquire. To tackle this issue, we propose an Attentionbased Multi-Context Guiding (A-MCG) network, which consists of three branches: the support branch, the query branch, the feature fusion branch. A key differentiator of A-MCG is the integration of multi-scale context features between support and query branches, enforcing a better guidance from the support set. In addition, we also adopt a spatial attention along the fusion branch to highlight context information from several scales, enhancing self-supervision in one-shot learning. To address the fusion problem in multi-shot learning, Conv-LSTM is adopted to collaboratively integrate the sequential support features to elevate the final accuracy. Our architecture obtains state-of-the-art on unseen classes in a variant of PASCAL VOC12 dataset and performs favorably against previous work with large gains of 1.1%, 1.4% measured in mIoU in the 1-shot and 5-shot setting.