A Learning Function for Parameter Reduction in Spiking Neural Networks with Radial Basis Function

Spiking neural networks - networks that encode information in the timing of spikes - are arising as a new approach in the artificial neural networks paradigm, emergent from cognitive science. One of these new models is the pulsed neural network with radial basis function, a network able to store information in the axonal propagation delay of neurons. Learning algorithms have been proposed to this model looking for mapping input pulses into output pulses. Recently, a new method was proposed to encode constant data into a temporal sequence of spikes, stimulating deeper studies in order to establish abilities and frontiers of this new approach. However, a well known problem of this kind of network is the high number of free parameters - more that 15 - to be properly configured or tuned in order to allow network convergence. This work presents for the first time a new learning function for this network training that allow the automatic configuration of one of the key network parameters: the synaptic weight decreasing factor.

Limnology of Macrobrachium amazonicum grow-out ponds subject to high inflow of nutrient-rich water and different stocking and harvest management

We evaluated the water characteristics and particle sedimentation in Macrobrachium amazonicum (Heller 1862) grow-out ponds supplied with a high inflow of nutrient-rich water. Prawns were subject to different stocking and harvesting strategies: upper-graded juveniles, lower-graded juveniles, non-graded juveniles + selective harvesting and traditional farming (non-grading juveniles and total harvest only). Dissolved oxygen, afternoon N-ammonia and N-nitrate and soluble orthophosphate were lower in the ponds in comparison with inflow water through the rearing cycle. Ponds stocked with the upper population fraction of graded prawns showed higher turbidity, total suspended solids and total Kjeldahl nitrogen than the remaining treatments. An increase in the chemical oxygen demand:biochemical oxygen demand ratio from inlet (4.9) to pond (7.1-8.0) waters indicated a non-readily biodegradable fraction enhancement in ponds. The sedimentation mean rate ranged from 0.08 to 0.16 mm day(-1) and sediment contained >80% of organic matter. The major factors affecting pond ecosystem dynamic were the organic load (due to primary production and feed addition) and bioturbation caused by stocking larger animals. Data suggest that M. amazonicum grow-out in ponds subjected to a high inflow of nutrient-rich water produce changes in the water properties, huge accumulation of organic sediment at the pond bottom and non-readily biodegradable material in the water column. However, the water quality remains suitable for aquaculture purposes. Therefore, nutrient-rich waters, when available, may represent a source of unpaid nutrients, which may be incorporated into economically valued biomass if managed properly.