Towards Evaluating the Reliability of Deep Neural Networks based IoT Devices

AbstractNowadays, deep neural networks (DNNs) have been rapidly deployed to realize a number of functionalities like sensing, imaging, classification, recognition, etc. However, the computational-intensive requirement of DNNs makes it difficult to be applicable for resource-limited Internet of Things (IoT) devices. In this paper, we propose a novel pruning-based paradigm that aims to reduce the computational cost of DNNs, by uncovering a more compact structure and learning the effective weights therein, on the basis of not compromising the expressive capability of DNNs. In particular, our algorithm can achieve efficient end-to-end training that transfers a redundant neural network to a compact one with a specifically targeted compression rate directly. We comprehensively evaluate our approach on various representative benchmark datasets and compared with typical advanced convolutional neural network (CNN) architectures. The experimental results verify the superior performance and robust effectiveness of our scheme. For example, when pruning VGG on CIFAR-10, our proposed scheme is able to significantly reduce its FLOPs (floating-point operations) and number of parameters with a proportion of 76.2% and 94.1%, respectively, while still maintaining a satisfactory accuracy. To sum up, our scheme could facilitate the integration of DNNs into the common machine-learning-based IoT framework and establish distributed training of neural networks in both cloud and edge.

Download Full-text

Performance of deep neural networks on low-power IoT devices

Proceedings of the Workshop on Benchmarking Cyber-Physical Systems and Internet of Things ◽

10.1145/3458473.3458823 ◽

2021 ◽

Author(s):

Christos Profentzas ◽

Magnus Almgren ◽

Olaf Landsiedel

Keyword(s):

Neural Networks ◽

Low Power ◽

Deep Neural Networks ◽

Iot Devices

Download Full-text

Designing Automated Deployment Strategies of Face Recognition Solutions in Heterogeneous IoT Platforms

Information ◽

10.3390/info12120532 ◽

2021 ◽

Vol 12 (12) ◽

pp. 532

Author(s):

Unai Elordi ◽

Chiara Lunerti ◽

Luis Unzueta ◽

Jon Goenetxea ◽

Nerea Aranjuelo ◽

...

Keyword(s):

Neural Networks ◽

Face Recognition ◽

Deep Neural Networks ◽

State Of The Art ◽

User Interaction ◽

Biometric Data ◽

Optimal Deployment ◽

Iot Platforms ◽

Iot Devices ◽

Hardware Platforms

In this paper, we tackle the problem of deploying face recognition (FR) solutions in heterogeneous Internet of Things (IoT) platforms. The main challenges are the optimal deployment of deep neural networks (DNNs) in the high variety of IoT devices (e.g., robots, tablets, smartphones, etc.), the secure management of biometric data while respecting the users’ privacy, and the design of appropriate user interaction with facial verification mechanisms for all kinds of users. We analyze different approaches to solving all these challenges and propose a knowledge-driven methodology for the automated deployment of DNN-based FR solutions in IoT devices, with the secure management of biometric data, and real-time feedback for improved interaction. We provide some practical examples and experimental results with state-of-the-art DNNs for FR in Intel’s and NVIDIA’s hardware platforms as IoT devices.

Download Full-text

Memory-Based Pruning of Deep Neural Networks for IoT Devices Applied to Flood Detection

Sensors ◽

10.3390/s21227506 ◽

2021 ◽

Vol 21 (22) ◽

pp. 7506

Author(s):

Francisco Erivaldo Fernandes Junior ◽

Luis Gustavo Nonato ◽

Caetano Mazzoni Ranieri ◽

Jó Ueyama

Keyword(s):

Neural Networks ◽

Control Systems ◽

Deep Neural Networks ◽

State Of The Art ◽

Damage Control ◽

Memory Footprint ◽

Flood Detection ◽

Iot Devices ◽

Internet Connections ◽

Flooding Events

Automatic flood detection may be an important component for triggering damage control systems and minimizing the risk of social or economic impacts caused by flooding. Riverside images from regular cameras are a widely available resource that can be used for tackling this problem. Nevertheless, state-of-the-art neural networks, the most suitable approach for this type of computer vision task, are usually resource-consuming, which poses a challenge for deploying these models within low-capability Internet of Things (IoT) devices with unstable internet connections. In this work, we propose a deep neural network (DNN) architecture pruning algorithm capable of finding a pruned version of a given DNN within a user-specified memory footprint. Our results demonstrate that our proposed algorithm can find a pruned DNN model with the specified memory footprint with little to no degradation of its segmentation performance. Finally, we show that our algorithm can be used in a memory-constraint wireless sensor network (WSN) employed to detect flooding events of urban rivers, and the resulting pruned models have competitive results compared with the original models.

Download Full-text

Adaptive Deep Neural Networks for the Internet of Things

International Journal of Sensors Wireless Communications and Control ◽

10.2174/2210327910666191223124630 ◽

2020 ◽

Vol 10 (4) ◽

pp. 570-581

Author(s):

Mohammad Khalid Pandit ◽

Roohie Naaz Mir ◽

Mohammad Ahsan Chishti

Keyword(s):

Neural Network ◽

Neural Networks ◽

Deep Neural Network ◽

Deep Neural Networks ◽

Feature Representations ◽

Network Layers ◽

Edge Location ◽

Iot Devices ◽

Private Network ◽

The Internet Of Things

Background: Deep neural networks have become the state of the art technology for real- world classification tasks due to their ability to learn better feature representations at each layer. However, the added accuracy that is associated with the deeper layers comes at a huge cost of computation, energy and added latency. Objective: The implementations of such architectures in resource constraint IoT devices are computationally prohibitive due to its computational and memory requirements. These factors are particularly severe in IoT domain. In this paper, we propose the Adaptive Deep Neural Network (ADNN) which gets split across the compute hierarchical layers i.e. edge, fog and cloud with all splits having one or more exit locations. Methods: At every location, the data sample adaptively chooses to exit from the NN (based on confidence criteria) or get fed into deeper layers housed across different compute layers. Design of ADNN, an adaptive deep neural network which results in fast and energy- efficient decision making (inference). : Joint optimization of all the exit points in ADNN such that the overall loss is minimized. Results: Experiments on MNIST dataset show that 41.9% of samples exit at the edge location (correctly classified) and 49.7% of samples exit at fog layer. Similar results are obtained on fashion MNIST dataset with only 19.4% of the samples requiring the entire neural network layers. With this architecture, most of the data samples are locally processed and classified while maintaining the classification accuracy and also keeping in check the communication, energy and latency requirements for time sensitive IoT applications. Conclusion: We investigated the approach of distributing the layers of the deep neural network across edge, fog and the cloud computing devices wherein data samples adaptively choose the exit points to classify themselves based on the confidence criteria (threshold). The results show that the majority of the data samples are classified within the private network of the user (edge, fog) while only a few samples require the entire layers of ADNN for classification.

Download Full-text

Zero-Keep Filter Pruning for Energy/Power Efficient Deep Neural Networks

Electronics ◽

10.3390/electronics10111238 ◽

2021 ◽

Vol 10 (11) ◽

pp. 1238

Author(s):

Yunhee Woo ◽

Dongyoung Kim ◽

Jaemin Jeong ◽

Young-Woong Ko ◽

Jeong-Gun Lee

Keyword(s):

Neural Networks ◽

Deep Learning ◽

High Performance ◽

Deep Neural Networks ◽

Learning Models ◽

Power Efficient ◽

Number Of Zeros ◽

Iot Devices ◽

Deep Learning Model ◽

Performance Computing

Recent deep learning models succeed in achieving high accuracy and fast inference time, but they require high-performance computing resources because they have a large number of parameters. However, not all systems have high-performance hardware. Sometimes, a deep learning model needs to be run on edge devices such as IoT devices or smartphones. On edge devices, however, limited computing resources are available and the amount of computation must be reduced to launch the deep learning models. Pruning is one of the well-known approaches for deriving light-weight models by eliminating weights, channels or filters. In this work, we propose “zero-keep filter pruning” for energy-efficient deep neural networks. The proposed method maximizes the number of zero elements in filters by replacing small values with zero and pruning the filter that has the lowest number of zeros. In the conventional approach, the filters that have the highest number of zeros are generally pruned. As a result, through this zero-keep filter pruning, we can have the filters that have many zeros in a model. We compared the results of the proposed method with the random filter pruning and proved that our method shows better performance with many fewer non-zero elements with a marginal drop in accuracy. Finally, we discuss a possible multiplier architecture, zero-skip multiplier circuit, which skips the multiplications with zero to accelerate and reduce energy consumption.

Download Full-text

Filter-Wise Quantization of Deep Neural Networks for IoT Devices

2021 IEEE International Conference on Consumer Electronics (ICCE) ◽

10.1109/icce50685.2021.9427656 ◽

2021 ◽

Author(s):

Hoseung Kim ◽

Geunhye Jo ◽

Hayun Lee ◽

Dongkun Shin

Keyword(s):

Neural Networks ◽

Deep Neural Networks ◽

Iot Devices

Download Full-text

Improving the Robustness of Model Compression by On-Manifold Adversarial Training

Future Internet ◽

10.3390/fi13120300 ◽

2021 ◽

Vol 13 (12) ◽

pp. 300

Author(s):

Junhyung Kwon ◽

Sangkyun Lee

Keyword(s):

Neural Networks ◽

Deep Neural Networks ◽

Prediction Performance ◽

Training Data ◽

Learning Technology ◽

Model Compression ◽

Robust Model ◽

Recent Developments ◽

Adversarial Training ◽

Iot Devices

Despite the advance in deep learning technology, assuring the robustness of deep neural networks (DNNs) is challenging and necessary in safety-critical environments, including automobiles, IoT devices in smart factories, and medical devices, to name a few. Furthermore, recent developments allow us to compress DNNs to reduce the size and computational requirements of DNNs to fit them into small embedded devices. However, how robust a compressed DNN can be has not been well studied in addressing its relationship to other critical factors, such as prediction performance and model sizes. In particular, existing studies on robust model compression have been focused on the robustness against off-manifold adversarial perturbation, which does not explain how a DNN will behave against perturbations that follow the same probability distribution as the training data. This aspect is relevant for on-device AI models, which are more likely to experience perturbations due to noise from the regular data observation environment compared with off-manifold perturbations provided by an external attacker. Therefore, this paper investigates the robustness of compressed deep neural networks, focusing on the relationship between the model sizes and the prediction performance on noisy perturbations. Our experiment shows that on-manifold adversarial training can be effective in building robust classifiers, especially when the model compression rate is high.

Download Full-text