Identification of finite state automata with a class of recurrent neural networks

Deep Mining from Omics Data

Since the advent of high-throughput omics technologies, various molecular data such as genes, transcripts, proteins, and metabolites have been made widely available to researchers. This has afforded clinicians, bioinformaticians, statisticians, and data scientists the opportunity to apply their innovations in feature mining and predictive modeling to a rich data resource to develop a wide range of generalizable prediction models. What has become apparent over the last 10 years is that researchers have adopted deep neural networks (or "deep nets") as their preferred paradigm of choice for complex data modeling due to the superiority of performance over more traditional statistical machine learning approaches, such as support vector machines. A key stumbling block, however, is that deep nets inherently lack transparency and are considered to be a "black box" approach. This naturally makes it very difficult for clinicians and other stakeholders to trust their deep learning models even though the model predictions appear to be highly accurate. In this chapter, we therefore provide a detailed summary of the deep net architectures typically used in omics research, together with a comprehensive summary of the notable "deep feature mining" techniques researchers have applied to open up this black box and provide some insights into the salient input features and why these models behave as they do. We group these techniques into the following three categories: (a) hidden layer visualization and interpretation; (b) input feature importance and impact evaluation; and (c) output layer gradient analysis. While we find that omics researchers have made some considerable gains in opening up the black box through interpretation of the hidden layer weights and node activations to identify salient input features, we highlight other approaches for omics researchers, such as employing deconvolutional network-based approaches and development of bespoke attribute impact measures to enable researchers to better understand the relationships between the input data and hidden layer representations formed and thus the output behavior of their deep nets.

Observability of Automata Networks: Fixed and Switching Cases

Automata networks are a class of fully discrete dynamical systems, which have received considerable interest in various different areas. This brief addresses the observability of automata networks and switched automata networks in a unified framework, and proposes simple necessary and sufficient conditions for observability. The results are achieved by employing methods from symbolic computation, and are suited for implementation using computer algebra systems. Several examples are presented to demonstrate the application of the results.

Evaluation of the vibration attenuation properties of an air-inflated cushion with two different heavy machinery seats in multi-axis vibration environments including jolts

Seats and cushions can attenuate whole-body vibration (WBV) exposures and minimize health risks for heavy machine operators. We successfully developed neural network (NN) algorithms to identify the vibration attenuation properties for four different seating conditions (seat/cushion combinations), and implemented each of the NN models to predict the equivalent daily exposure A(8) values for various vehicles in the forestry and mining environments. We also evaluated the performance of the new prototype No-Jolt™ air-inflated cushion and the original cushion of each seat with jolt exposures. We observed that the air cushion significantly improved the vibration attenuation properties of the seat that initially had good performance, but not for the seat that had relatively poor vibration attenuation properties. In addition, operator's anthropometrics and sex influenced the performance of the air-inflated cushion when the vibration environment included jolt exposures.

The Kernel Adaptive Autoregressive-Moving-Average Algorithm

In this paper, we present a novel kernel adaptive recurrent filtering algorithm based on the autoregressive-moving-average (ARMA) model, which is trained with recurrent stochastic gradient descent in the reproducing kernel Hilbert spaces. This kernelized recurrent system, the kernel adaptive ARMA (KAARMA) algorithm, brings together the theories of adaptive signal processing and recurrent neural networks (RNNs), extending the current theory of kernel adaptive filtering (KAF) using the representer theorem to include feedback. Compared with classical feedforward KAF methods, the KAARMA algorithm provides general nonlinear solutions for complex dynamical systems in a state-space representation, with a deferred teacher signal, by propagating forward the hidden states. We demonstrate its capabilities to provide exact solutions with compact structures by solving a set of benchmark nondeterministic polynomial-complete problems involving grammatical inference. Simulation results show that the KAARMA algorithm outperforms equivalent input-space recurrent architectures using first- and second-order RNNs, demonstrating its potential as an effective learning solution for the identification and synthesis of deterministic finite automata.

Discrete-time neural inverse optimal control for nonlinear systems via passivation

This paper presents a discrete-time inverse optimal neural controller, which is constituted by combination of two techniques: 1) inverse optimal control to avoid solving the Hamilton-Jacobi-Bellman equation associated with nonlinear system optimal control and 2) on-line neural identification, using a recurrent neural network trained with an extended Kalman filter, in order to build a model of the assumed unknown nonlinear system. The inverse optimal controller is based on passivity theory. The applicability of the proposed approach is illustrated via simulations for an unstable nonlinear system and a planar robot.