Neural architecture search (NAS) has attracted increasing attentions in both academia and industry. In the early age, researchers mostly applied individual search methods which sample and evaluate the candidate architectures separately and thus incur heavy computational overheads. To alleviate the burden, weight-sharing methods were proposed in which exponentially many architectures share weights in the same super-network, and the costly training procedure is performed only once. These methods, though being much faster, often suffer the issue of instability. This paper provides a literature review on NAS, in particular the weight-sharing methods, and points out that the major challenge comes from the optimization gap between the super-network and the sub-architectures. From this perspective, we summarize existing approaches into several categories according to their efforts in bridging the gap, and analyze both advantages and disadvantages of these methodologies. Finally, we share our opinions on the future directions of NAS and AutoML. Due to the expertise of the authors, this paper mainly focuses on the application of NAS to computer vision problems and may bias towards the work in our group.

Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap

A variety of methods have been applied to the architectural configuration and learning or training of artificial deep neural networks (DNN). These methods play a crucial role in the success or failure of the DNN for most problems and applications. Evolutionary Algorithms (EAs) are gaining momentum as a computationally feasible method for the automated optimisation and training of DNNs. Neuroevolution is a term which describes these processes of automated configuration and training of DNNs using EAs. While many works exist in the literature, no comprehensive surveys currently exist focusing exclusively on the strengths and limitations of using neuroevolution approaches in DNNs. Prolonged absence of such surveys can lead to a disjointed and fragmented field preventing DNNs researchers potentially adopting neuroevolutionary methods in their own research, resulting in lost opportunities for improving performance and wider application within real-world deep learning problems. This paper presents a comprehensive survey, discussion and evaluation of the state-of-the-art works on using EAs for architectural configuration and training of DNNs. Based on this survey, the paper highlights the most pertinent current issues and challenges in neuroevolution and identifies multiple promising future research directions.

Neuroevolution in Deep Neural Networks: Current Trends and Future Challenges

Deep neural networks (DNNs) have evolved as a beneficial machine learning method that has been successfully used in various applications. Currently, DNN is a superior technique of extracting information from massive sets of data in a self-organized method. DNNs have different structures and parameters, which are usually produced for particular applications. Nevertheless, the training procedures of DNNs can be protracted depending on the given application and the size of the training set. Further, determining the most precise and practical structure of a deep learning method in a reasonable time is a possible problem related to this procedure. Meta-heuristics techniques, such as swarm intelligence (SI) and evolutionary computing (EC), represent optimization frames with specific theories and objective functions. These methods are adjustable and have been demonstrated their effectiveness in various applications; hence, they can optimize the DNNs models. This paper presents a comprehensive survey of the recent optimization methods (i.e., SI and EC) employed to enhance DNNs performance on various tasks. This paper also analyzes the importance of optimization methods in generating the optimal hyper-parameters and structures of DNNs in taking into consideration massive-scale data. Finally, several potential directions that still need improvements and open problems in evolutionary DNNs are identified.

Advanced metaheuristic optimization techniques in applications of deep neural networks: a review

A variety of methods have been applied to the architectural configuration and learning or training of artificial deep neural networks (DNN). These methods play a crucial role in the success or failure of the DNN for most problems and applications. Evolutionary Algorithms (EAs) are gaining momentum as a computationally feasible method for the au- tomated optimisation of DNNs. Neuroevolution is a term which describes these processes of automated configuration and training of DNNs using EAs. While many works exist in the literature, no comprehensive surveys currently exist focusing exclusively on the strengths and limitations of using neuroevolution approaches in DNNs. Prolonged absence of such surveys can lead to a disjointed and fragmented field preventing DNNs researchers potentially adopting neuroevolutionary methods in their own research, resulting in lost opportunities for improving perfor- mance and wider application within real-world deep learning problems. This paper presents a comprehensive survey, discussion and evaluation of the state-of-the-art works on using EAs for architectural configuration and training of DNNs. Based on this survey, the paper highlights the most pertinent current issues and challenges in neuroevolution and identifies multiple promising future research directions.

The great advancements in communication, cloud computing, and the internet of things (IoT) have opened critical challenges in security. With these developments, cyberattacks are also rapidly growing since the current security mechanisms do not provide efficient solutions. Recently, various artificial intelligence (AI) based solutions have been proposed for different security applications, including intrusion detection. In this paper, we propose an efficient AI-based mechanism for intrusion detection systems (IDS) in IoT systems. We leverage the advancements of deep learnings and metaheuristics (MH) algorithms that approved their efficiency in solving complex engineering problems. We propose a feature extraction method using the convolutional neural networks (CNNs) to extract relevant features. Also, we develop a new feature selection method using a new variant of the transient search optimization (TSO) algorithm, called TSODE, using the operators of differential evolution (DE) algorithm. The proposed TSODE uses the DE to improve the process of balancing between exploitation and exploration phases. Furthermore, we use three public datasets, KDDCup-99, NSL-KDD, BoT-IoT, and CICIDS-2017 to assess the performance of the developed method, which achieved higher accuracy compared to several existing approaches.

/pdf/iot-intrusion-detection-system-using-deep-learning-and-4e40jk8krj.pdf

IoT Intrusion Detection System Using Deep Learning and Enhanced Transient Search Optimization

This paper presents a new algorithm, Evolutionary eXploration of Augmenting Memory Models (EXAMM), which is capable of evolving recurrent neural networks (RNNs) using a wide variety of memory structures, such as Δ-RNN, GRU, LSTM, MGU and UGRNN cells. EXAMM evolved RNNs to perform prediction of large-scale, real world time series data from the aviation and power industries. These data sets consist of very long time series (thousands of readings), each with a large number of potentially correlated and dependent parameters. Four different parameters were selected for prediction and EXAMM runs were performed using each memory cell type alone, each cell type and simple neurons, and with all possible memory cell types and simple neurons. Evolved RNN performance was measured using repeated k-fold cross validation, resulting in 2420 EXAMM runs which evolved 4, 840, 000 RNNs in ~24,200 CPU hours on a high performance computing cluster. Generalization of the evolved RNNs was examined statistically, providing findings that can help refine the design of RNN memory cells as well as inform future neuro-evolution algorithms.

Investigating recurrent neural network memory structures using neuro-evolution

This paper presents a new algorithm, Evolutionary eXploration of Augmenting Memory Models (EXAMM), which is capable of evolving recurrent neural networks (RNNs) using a wide variety of memory structures, such as Delta-RNN, GRU, LSTM, MGU and UGRNN cells. EXAMM evolved RNNs to perform prediction of large-scale, real world time series data from the aviation and power industries. These data sets consist of very long time series (thousands of readings), each with a large number of potentially correlated and dependent parameters. Four different parameters were selected for prediction and EXAMM runs were performed using each memory cell type alone, each cell type with feed forward nodes, and with all possible memory cell types. Evolved RNN performance was measured using repeated k-fold cross validation, resulting in 1210 EXAMM runs which evolved 2,420,000 RNNs in 12,100 CPU hours on a high performance computing cluster. Generalization of the evolved RNNs was examined statistically, providing interesting findings that can help refine the RNN memory cell design as well as inform future neuro-evolution algorithms development.

Ahmed Ahmed Elsaid

Papers

Investigating recurrent neural network memory structures using neuro-evolution

Investigating RNN Memory using Neuro-Evolution: Investigating Recurrent Neural Network Memory Structures using Neuro-Evolution

Investigating Recurrent Neural Network Memory Structures using Neuro-Evolution