A 3D ray traced biological neural network learning model.

Training large neural networks on big datasets requires significant computational resources and time. Transfer learning reduces training time by pre-training a base model on one dataset and transferring the knowledge to a new model for another dataset. However, current choices of transfer learning algorithms are limited because the transferred models always have to adhere to the dimensions of the base model and can not easily modify the neural architecture to solve other datasets. On the other hand, biological neural networks (BNNs) are adept at rearranging themselves to tackle completely different problems using transfer learning. Taking advantage of BNNs, we design a dynamic neural network that is transferable to any other network architecture and can accommodate many datasets. Our approach uses raytracing to connect neurons in a three-dimensional space, allowing the network to grow into any shape or size. In the Alcala dataset, our transfer learning algorithm trains the fastest across changing environments and input sizes. In addition, we show that our algorithm also outperformance the state of the art in EEG dataset. In the future, this network may be considered for implementation on real biological neural networks to decrease power consumption.

Universal activation function for machine learning.

This article proposes a universal activation function (UAF) that achieves near optimal performance in quantification, classification, and reinforcement learning (RL) problems. For any given problem, the gradient descent algorithms are able to evolve the UAF to a suitable activation function by tuning the UAF's parameters. For the CIFAR-10 classification using the VGG-8 neural network, the UAF converges to the Mish like activation function, which has near optimal performance [Formula: see text] when compared to other activation functions. In the graph convolutional neural network on the CORA dataset, the UAF evolves to the identity function and obtains [Formula: see text]. For the quantification of simulated 9-gas mixtures in 30 dB signal-to-noise ratio (SNR) environments, the UAF converges to the identity function, which has near optimal root mean square error of [Formula: see text]. In the ZINC molecular solubility quantification using graph neural networks, the UAF morphs to a LeakyReLU/Sigmoid hybrid and achieves RMSE=[Formula: see text]. For the BipedalWalker-v2 RL dataset, the UAF achieves the 250 reward in [Formula: see text] epochs with a brand new activation function, which gives the fastest convergence rate among the activation functions.

Localization algorithms for asynchronous time difference of arrival positioning systems.

An asynchronous time difference of arrival (ATDOA) positioning system requires no time synchronization among all the anchor and target nodes, which makes it highly practical and can be easily deployed. This paper first presents an ATDOA localization model, and then primarily focuses on two new localization algorithms for the system. The first algorithm is a two-step positioning algorithm that combines semidefinite programming (SDP) with a Taylor series method to achieve global convergence as well as superior estimation accuracy, and the second algorithm is a constrained least-squares method that has the advantage of low complexity and fast convergence while maintaining good performance. In addition, a novel receiver re-selection method is presented to significantly improve estimation accuracy. In this paper, we also derive the Cramer-Rao lower bound (CRLB) of the ATDOA positioning system using a distance-dependent noise variance model, which describes a realistic indoor propagation channel.