DNA dynamics and computation based on toehold-free strand displacement.

We present a simple and effective scheme of a dynamic switch for DNA nanostructures. Under such a framework of toehold-free strand displacement, blocking strands at an excess amount are applied to displace the complementation of specific segments of paired duplexes. The functional mechanism of the scheme is illustrated by modelling the base pairing kinetics of competing strands on a target strand. Simulation reveals the unique properties of toehold-free strand displacement in equilibrium control, which can be leveraged for information processing. Based on the controllable dynamics in the binding of preformed DNA nanostructures, a multi-input-multi-output (MIMO) Boolean function is controlled by the presence of the blockers. In conclusion, we implement two MIMO Boolean functions (one with 4-bit input and 2-bit output, and the other with 16-bit input and 8-bit output) to showcase the controllable dynamics.

Deep Learning-Based Model Predictive Control for Continuous Stirred-Tank Reactor System.

A continuous stirred-tank reactor (CSTR) system is widely applied in wastewater treatment processes. Its control is a challenging industrial-process-control problem due to great difficulty to achieve accurate system identification. This work proposes a deep learning-based model predictive control (DeepMPC) to model and control the CSTR system. The proposed DeepMPC consists of a growing deep belief network (GDBN) and an optimal controller. First, GDBN can automatically determine its size with transfer learning to achieve high performance in system identification, and it serves just as a predictive model of a controlled system. The model can accurately approximate the dynamics of the controlled system with a uniformly ultimately bounded error. Second, quadratic optimization is conducted to obtain an optimal controller. This work analyzes the convergence and stability of DeepMPC. Finally, the DeepMPC is used to model and control a second-order CSTR system. In the experiments, DeepMPC shows a better performance in modeling, tracking, and antidisturbance than the other state-of-the-art methods.

An Adaptive Deep Belief Network With Sparse Restricted Boltzmann Machines.

Deep belief network (DBN) is an efficient learning model for unknown data representation, especially nonlinear systems. However, it is extremely hard to design a satisfactory DBN with a robust structure because of traditional dense representation. In addition, backpropagation algorithm-based fine-tuning tends to yield poor performance since its ease of being trapped into local optima. In this article, we propose a novel DBN model based on adaptive sparse restricted Boltzmann machines (AS-RBM) and partial least square (PLS) regression fine-tuning, abbreviated as ARP-DBN, to obtain a more robust and accurate model than the existing ones. First, the adaptive learning step size is designed to accelerate an RBM training process, and two regularization terms are introduced into such a process to realize sparse representation. Second, initial weight derived from AS-RBM is further optimized via layer-by-layer PLS modeling starting from the output layer to input one. Third, we present the convergence and stability analysis of the proposed method. Finally, our approach is tested on Mackey-Glass time-series prediction, 2-D function approximation, and unknown system identification. Simulation results demonstrate that it has higher learning accuracy and faster learning speed. It can be used to build a more robust model than the existing ones.

A sparse deep belief network with efficient fuzzy learning framework.

Deep belief network (DBN) is one of the most feasible ways to realize deep learning (DL) technique, and it has been attracting more and more attentions in nonlinear system modeling. However, DBN cannot provide satisfactory results in learning speed, modeling accuracy and robustness, which is mainly caused by dense representation and gradient diffusion. To address these problems and promote DBN's development in cross-models, we propose a Sparse Deep Belief Network with Fuzzy Neural Network (SDBFNN) for nonlinear system modeling. In this novel framework, the sparse DBN is considered as a pre-training technique to realize fast weight-initialization and to obtain feature vectors. It can balance the dense representation to improve its robustness. A fuzzy neural network is developed for supervised modeling so as to eliminate the gradient diffusion. Its input happens to be the obtained feature vector. As a novel cross-model, SDBFNN combines the advantages of both pre-training technique and fuzzy neural network to improve modeling capability. Its convergence is also analyzed as well. A benchmark problem and a practical problem in wastewater treatment are conducted to demonstrate the superiority of SDBFNN. The extensive experimental results show that SDBFNN achieves better performance than the existing methods in learning speed, modeling accuracy and robustness.

Efficient Computing Budget Allocation for Finding Simplest Good Designs.

In many applications some designs are easier to implement, require less training data and shorter training time, and consume less storage than the others. Such designs are called simple designs, and are usually preferred over complex ones when they all have good performance. Despite the abundant existing studies on how to find good designs in simulation-based optimization (SBO), there exist few studies on finding simplest good designs. We consider this important problem in this paper, and make the following contributions. First, we provide lower bounds for the probabilities of correctly selecting the m simplest designs with top performance, and selecting the best m such simplest good designs, respectively. Second, we develop two efficient computing budget allocation methods to find m simplest good designs and to find the best m such designs, respectively; and show their asymptotic optimalities. Third, we compare the performance of the two methods with equal allocations over 6 academic examples and a smoke detection problem in wireless sensor networks. We hope that this work brings insight to finding the simplest good designs in general.