Recurrent neural networks (RNNs) are a powerful approach for time series prediction. However, their performance is strongly affected by their architecture and hyperparameter settings. The... Show moreRecurrent neural networks (RNNs) are a powerful approach for time series prediction. However, their performance is strongly affected by their architecture and hyperparameter settings. The architecture optimization of RNNs is a time-consuming task, where the search space is typically a mixture of real, integer and categorical values. To allow for shrinking and expanding the size of the network, the representation of architectures often has a variable length. In this paper, we propose to tackle the architecture optimization problem with a variant of the Bayesian Optimization (BO) algorithm. To reduce the evaluation time of candidate architectures the Mean Absolute Error Random Sampling (MRS), a training-free method to estimate the network performance, is adopted as the objective function for BO. Also, we propose three fixed-length encoding schemes to cope with the variable-length architecture representation. The result is a new perspective on accurate and efficient design of RNNs, that we validate on three problems. Our findings show that 1) the BO algorithm can explore different network architectures using the proposed encoding schemes and successfully designs well-performing architectures, and 2) the optimization time is significantly reduced by using MRS, without compromising the performance as compared to the architectures obtained from the actual training procedure. Show less
Neural Architecture Search (NAS) aims to optimize deep neural networks' architecture for better accuracy or smaller computational cost and has recently gained more research interests. Despite... Show moreNeural Architecture Search (NAS) aims to optimize deep neural networks' architecture for better accuracy or smaller computational cost and has recently gained more research interests. Despite various successful approaches proposed to solve the NAS task, the landscape of it, along with its properties, are rarely investigated. In this paper, we argue for the necessity of studying the landscape property thereof and propose to use the so-called Exploratory Landscape Analysis (ELA) techniques for this goal. Taking a broad set of designs of the deep convolutional network, we conduct extensive experimentation to obtain their performance. Based on our analysis of the experimental results, we observed high similarities between well-performing architecture designs, which is then used to significantly narrow the search space to improve the efficiency of any NAS algorithm. Moreover, we extract the ELA features over the NAS landscapes on three common image classification data sets, MNIST, Fashion, and CIFAR-10, which shows that the NAS landscape can be distinguished for those three data sets. Also, when comparing to the ELA features of the well-known Black-Box optimization Benchmarking (BBOB) problem set, we found out that the NAS landscapes surprisingly form a new problem class on its own, which can be separated from all 24 BBOB problems. Given this interesting observation, we, therefore, state the importance of further investigation on selecting an efficient optimizer for the NAS landscape as well as the necessity of augmenting the current benchmark problem set. Show less
Stem cells with the capability to self-renew and differentiate into multiple cell derivatives provide platforms for drug screening and promising treatment options for a wide variety of neural... Show moreStem cells with the capability to self-renew and differentiate into multiple cell derivatives provide platforms for drug screening and promising treatment options for a wide variety of neural diseases. Nevertheless, clinical applications of stem cells have been hindered partly owing to a lack of standardized techniques to characterize cell molecular profiles noninvasively and comprehensively. Here, we demonstrate that a label-free and noninvasive single-cell Raman microspectroscopy (SCRM) platform was able to identify neural cell lineages derived from clinically relevant human induced pluripotent stem cells (hiPSCs). By analyzing the intrinsic biochemical profiles of single cells at a large scale (8,774 Raman spectra in total), iPSCs and iPSC-derived neural cells can be distinguished by their intrinsic phenotypic Raman spectra. We identified a Raman biomarker from glycogen to distinguish iPSCs from their neural derivatives, and the result was verified by the conventional glycogen detection assays. Further analysis with a machine learning classification model, utilizing t-distributed stochastic neighbor embedding (t-SNE)-enhanced ensemble stacking, clearly categorized hiPSCs in different develop- mental stages with 97.5% accuracy. The present study demon-strates the capability of the SCRM-based platform to monitor cell development using high content screening with a noninvasive and label-free approach. This platform as well as our identified bio- marker could be extensible to other cell types and can potentially have a high impact on neural stem cell therapy. Show less
Plants and vegetation play a critical-but largely unpredictable-role in global environmental changes due to the multitude of contributing processes at widely different spatial and temporal scales.... Show morePlants and vegetation play a critical-but largely unpredictable-role in global environmental changes due to the multitude of contributing processes at widely different spatial and temporal scales. In this Perspective, we explore approaches to master this complexity and improve our ability to predict vegetation dynamics by explicitly taking account of principles that constrain plant and ecosystem behaviour: natural selection, self-organization and entropy maximization. These ideas are increasingly being used in vegetation models, but we argue that their full potential has yet to be realized. We demonstrate the power of natural selection-based optimality principles to predict photosynthetic and carbon allocation responses to multiple environmental drivers, as well as how individual plasticity leads to the predictable self-organization of forest canopies. We show how models of natural selection acting on a few key traits can generate realistic plant communities and how entropy maximization can identify the most probable outcomes of community dynamics in space- and time-varying environments. Finally, we present a roadmap indicating how these principles could be combined in a new generation of models with stronger theoretical foundations and an improved capacity to predict complex vegetation responses to environmental change.Integrating natural selection and other organizing principles into next-generation vegetation models could render them more theoretically sound and useful for earth system applications and modelling climate impacts. Show less
Wang, H.; Emmerich, M.T.M.; Preuss, M.; Plaat, A. 2020
Recently, AlphaZero has achieved outstanding performance in playing Go, Chess, and Shogi. Players in AlphaZero consist of a combination of Monte Carlo Tree Search and a deep neural network, that is... Show moreRecently, AlphaZero has achieved outstanding performance in playing Go, Chess, and Shogi. Players in AlphaZero consist of a combination of Monte Carlo Tree Search and a deep neural network, that is trained using self-play. The unified deep neural network has a policy-head and a value-head, and during training, the optimizer minimizes the sum of policy loss and value loss. However, it is not clear if and under which circumstances other formulations of the loss function are better. Therefore, we perform experiments with different combinations of these two minimization targets. In contrast to many recent papers who adopt single run experiments and use the whole history Elo ratings from self-play, we propose to use repeated runs. The results show that this method can describe the training performance quite well within each training run, but there is a high self-play bias, such that it is incomparable among different training runs. Therefore, inspired by the AlphaGo series papers, a self-play bias avoiding performance assessment, final best player Elo rating, is adopted to evaluate the playing strength in a direct competition between the evolved players. For relatively small games, based on this new evaluation method, surprisingly, minimizing only value loss achieves the strongest playing strength in the final best players' round-robin tournament. These results indicate that more research is needed into the relative importance of value function and policy function in small games. Show less
This paper investigates whether optimisation methods with the population made up of one solution can suffer from structural bias just like their multisolution variants. Following recent results... Show moreThis paper investigates whether optimisation methods with the population made up of one solution can suffer from structural bias just like their multisolution variants. Following recent results highlighting the importance of choice of strategy for handling solutions generated outside the domain, a selection of single solution methods are considered in conjunction with several such strategies. Obtained results are tested for the presence of structural bias by means of a traditional approach from literature and a newly proposed here statistical approach. These two tests are demonstrated to be not fully consistent. All tested methods are found to be structurally biased with at least one of the tested strategies. Confirming results for multisolution methods, it is such strategy that is shown to control the emergence of structural bias in single solution methods. Some of the tested methods exhibit a kind of structural bias that has not been observed before. Show less
Combinatorial optimization is an important application targeted by quantum computing. However, near-term hardware constraints make quantum algorithms unlikely to be competitive when compared to... Show moreCombinatorial optimization is an important application targeted by quantum computing. However, near-term hardware constraints make quantum algorithms unlikely to be competitive when compared to high-performing classical heuristics on large practical problems. One option to achieve advantages with near-term devices is to use them in combination with classical heuristics. In particular, we propose using quantum methods to sample from classically intractable distributions -- which is the most probable approach to attain a true provable quantum separation in the near-term -- which are used to solve optimization problems faster. We numerically study this enhancement by an adaptation of Tabu Search using the Quantum Approximate Optimization Algorithm (QAOA) as a neighborhood sampler. We show that QAOA provides a flexible tool for exploration-exploitation in such hybrid settings and can provide evidence that it can help in solving problems faster by saving many tabu iterations and achieving better solutions. Show less
When faced with a specific optimization problem, choosing which algorithm to use is always a tough task. Not only is there a vast variety of algorithms to select from, but these algorithms often... Show moreWhen faced with a specific optimization problem, choosing which algorithm to use is always a tough task. Not only is there a vast variety of algorithms to select from, but these algorithms often are controlled by many hyperparameters, which need to be tuned in order to achieve the best performance possible. Usually, this problem is separated into two parts: algorithm selection and algorithm configuration. With the significant advances made in Machine Learning, however, these problems can be integrated into a combined algorithm selection and hyperparameter optimization task, commonly known as the CASH problem. In this work we compare sequential and integrated algorithm selection and configuration approaches for the case of selecting and tuning the best out of 4608 variants of the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) tested on the Black Box Optimization Benchmark (BBOB) suite. We first show that the ranking of the modular CMA-ES variants depends to a large extent on the quality of the hyperparameters. This implies that even a sequential approach based on complete enumeration of the algorithm space will likely result in sub-optimal solutions. In fact, we show that the integrated approach manages to provide competitive results at a much smaller computational cost. We also compare two different mixed-integer algorithm configuration techniques, called irace and Mixed-Integer Parallel Efficient Global Optimization (MIP-EGO). While we show that the two methods differ significantly in their treatment of the exploration-exploitation balance, their overall performances are very similar. Show less
