Improving Recall Accuracy in Sparse Associative Memories That Use Neurogenesis.

The creation of future low-power neuromorphic solutions requires specialist spiking neural network (SNN) algorithms that are optimized for neuromorphic settings. One such algorithmic challenge is the ability to recall learned patterns from their noisy variants. Solutions to this problem may be required to memorize vast numbers of patterns based on limited training data and subsequently recall the patterns in the presence of noise.

How Convolutional Neural Network Architecture Biases Learned Opponency and Color Tuning.

Recent work suggests that changing convolutional neural network (CNN) architecture by introducing a bottleneck in the second layer can yield changes in learned function. To understand this relationship fully requires a way of quantitatively comparing trained networks. The fields of electrophysiology and psychophysics have developed a wealth of methods for characterizing visual systems that permit such comparisons.

Deep Cascade Learning.

In this paper, we propose a novel approach for efficient training of deep neural networks in a bottom-up fashion using a layered structure. Our algorithm, which we refer to as deep cascade learning, is motivated by the cascade correlation approach of Fahlman and Lebiere, who introduced it in the context of perceptrons. We demonstrate our algorithm on networks of convolutional layers, though its applicability is more general.

Trophodynamics of some PFCs and BFRs in a western Canadian Arctic marine food web.

The trophodynamics of per- and polyfluorinated compounds and bromine-based flame retardants were examined in components of a marine food web from the western Canadian Arctic. The animals studied and their relative trophic status in the food web, established using stable isotopes of nitrogen (delta15N), were beluga (Delphinapterus leucas) > ringed seal (Phoca hispida) > Arctic cod (Boreogadus saida) > Pacific herring (Clupea pallasi) approximately equal to Arctic cisco (Coregonus autumnalis) > pelagic amphipod (Themisto libellula) > Arctic copepod (Calanus hyperboreus). For the brominated diphenyl ethers, the lipid adjusted concentrations of the seven congeners analyzed (Sigma7BDEs: -47, -85, -99, -100, -153, -154, and -209) ranged from 205.

Examination of isomer specific bioaccumulation parameters and potential in vivo hepatic metabolites of syn- and anti-Dechlorane Plus isomers in juvenile rainbow trout (Oncorhynchus mykiss).

Juvenile rainbow trout (Oncorhynchus mykiss) were exposed in the laboratory to elevated doses of syn- and anti-isomers of Dechlorane Plus (DP) via their diet for 49 days (uptake phase), followed by 112 days of untreated food (depuration phase) to examine bioaccumulation parameters and possible metabolic products. Three groups of 60 fish were used in the study. Two groups were exposed separately to food fortified with known concentrations of syn- (0.