PerfSeer: An Efficient and Accurate Deep Learning Models Performance Predictor

Deep learning is employed in many applications, such as computer vision, natural language processing, robotics, and recommender systems. Large and complex neural networks lead to high accuracy; however, they adversely affect many aspects of deep learning performance, such as training time, latency, throughput, energy consumption, and memory usage in the training and inference stages. To solve these challenges, various optimization techniques and frameworks have been developed for the efficient performance of deep learning models in the training and inference stages. Although optimization techniques such as quantization have been studied thoroughly in the past, less work has been done to study the performance of frameworks that provide quantization techniques. In this paper, we have used different performance metrics to study the performance of various quantization frameworks, including TensorFlow automatic mixed precision and TensorRT. These performance metrics include training time and memory utilization in the training stage along with latency and throughput for graphics processing units (GPUs) in the inference stage. We have applied the automatic mixed precision (AMP) technique during the training stage using the TensorFlow framework, while for inference we have utilized the TensorRT framework for the post-training quantization technique using the TensorFlow TensorRT (TF-TRT) application programming interface (API).We performed model profiling for different deep learning models, datasets, image sizes, and batch sizes for both the training and inference stages, the results of which can help developers and researchers to devise and deploy efficient deep learning models for GPUs.

Area under the curve may hide poor generalisation to external datasets

Deep learning breast cancer risk models demonstrate improved accuracy compared with traditional risk models but have not been prospectively tested. We compared the accuracy of a deep learning risk score derived from the patient's prior mammogram to traditional risk scores to prospectively identify patients with cancer in a cohort due for screening. We collected data on 119 139 bilateral screening mammograms in 57 617 consecutive patients screened at 5 facilities between September 18, 2017, and February 1, 2021. Patient demographics were retrieved from electronic medical records, cancer outcomes determined through regional tumor registry linkage, and comparisons made across risk models using Wilcoxon and Pearson χ2 2-sided tests. Deep learning, Tyrer-Cuzick, and National Cancer Institute Breast Cancer Risk Assessment Tool (NCI BCRAT) risk models were compared with respect to performance metrics and area under the receiver operating characteristic curves. Cancers detected per thousand patients screened were higher in patients at increased risk by the deep learning model (8.6, 95% confidence interval [CI] = 7.9 to 9.4) compared with Tyrer-Cuzick (4.4, 95% CI = 3.9 to 4.9) and NCI BCRAT (3.8, 95% CI = 3.3 to 4.3) models (P < .001). Area under the receiver operating characteristic curves of the deep learning model (0.68, 95% CI = 0.66 to 0.70) was higher compared with Tyrer-Cuzick (0.57, 95% CI = 0.54 to 0.60) and NCI BCRAT (0.57, 95% CI = 0.54 to 0.60) models. Simulated screening of the top 50th percentile risk by the deep learning model captured statistically significantly more patients with cancer compared with Tyrer-Cuzick and NCI BCRAT models (P < .001). A deep learning model to assess breast cancer risk can support feasible and effective risk-based screening and is superior to traditional models to identify patients destined to develop cancer in large screening cohorts.

Predicting energy consumption of mosque buildings during the operation stage using deep learning approach

Soil temperature (ST) plays an important role in agriculture and other fields, and has a close relationship with plant growth and development. Therefore, accurate ST prediction methods are widely needed. Deep learning (DL) models have been widely applied for ST prediction. However, the traditional DL models may fail to capture the spatiotemporal relationship due to its complex dependency under different related hydrologic variables. Hence, the DL models with Ensemble Empirical Mode Decomposition (EEMD) are proposed in this study. The proposed models can capture more complex spatiotemporal relationship after decomposing the ST into different intrinsic mode functions. Therefore, the performance of models is further improved. The results show that the performance of DL models with EEMD are better than that of corresponding DL models without EEMD. Moreover, EEMD-Conv3d has the best performance among all the experimental models. It has the highest R2 ranging from 0.9826 to 0.9893, the lowest RMSE ranging from 1.3096 to 1.6497 and the lowest MAE ranging from 0.9656 to 1.2056 in predicting ST at the lead time from one to five days. In addition, the lines between predicted ST and observed ST are closer to the ideal line (y = x) than other DL models. The results show that our EEMD-Conv3D can better capture spatiotemporal correlation and is an applicable method for predicting spatiotemporal ST.

The past few years have seen a surge of applying Deep Learning (DL) models for a wide array of tasks such as image classification, object detection, machine translation, etc. While DL models provide an opportunity to solve otherwise intractable tasks, their adoption relies on them being optimized to meet latency and resource requirements. Benchmarking is a key step in this process but has been hampered in part due to the lack of representative and up-to-date benchmarking suites. This is exacerbated by the fast-evolving pace of DL models. This paper proposes DLBricks, a composable benchmark generation design that reduces the effort of developing, maintaining, and running DL benchmarks on CPUs. DLBricks decomposes DL models into a set of unique runnable networks and constructs the original model's performance using the performance of the generated benchmarks. DLBricks leverages two key observations: DL layers are the performance building blocks of DL models and layers are extensively repeated within and across DL models. Since benchmarks are generated automatically and the benchmarking time is minimized, DLBricks can keep up-to-date with the latest proposed models, relieving the pressure of selecting representative DL models. Moreover, DLBricks allows users to represent proprietary models within benchmark suites. We evaluate DLBricks using $50$ MXNet models spanning $5$ DL tasks on $4$ representative CPU systems. We show that DLBricks provides an accurate performance estimate for the DL models and reduces the benchmarking time across systems (e.g. within $95\%$ accuracy and up to $4.4\times$ benchmarking time speedup on Amazon EC2 c5.xlarge).

For Heterogeneous Multi-Processor System-on-Chips (HMPSoCs), a reasonable pipeline design can significantly improve the inference performance of Deep Learning (DL) models. The pipeline design optimization can be modeled as a search problem where an accurate prediction model can efficiently speed up the search process. However, the performance prediction of DL models for the pipeline inference strategy is challenging because of the inter-layer effect, inference details, and variety of model structures. In this paper, we propose TPPNet, a transformer-based model for predicting the inference performance of various DL models with the pipeline inference strategy. TPPNet represents the DL model as an execution sequence with operators and hardware details to extract the hidden factors between layers. Moreover, we apply the Multi-task Learning (MTL) method to accurately predict throughput and latency metrics by constructing a predictive model. To the best of our knowledge, this is the first study dedicated to pipeline inference performance prediction for the DL model on HMPSoCs. We evaluate TPPNet on six well-known DL models using RK3399. The experimental outcomes affirm the high accuracy of TPPNet and its capability to significantly reduce the time overhead associated with pipeline exploration.

Lyme disease is one of the most common vector-borne infections. It typically causes cardiac illnesses, neurologic illnesses, musculoskeletal disorders, and dermatologic conditions. However, most of the time, it is poorly diagnosed due to many similarities with other diseases such as drug rash. Given the potentially serious consequences of unnecessary antimicrobial treatments, it is essential to understand frequent and uncommon diagnoses that explain symptoms in this population. Recently, deep learning models have been used for the diagnosis of various rash-related diseases. However, these models suffer from overfitting and color variation problems. To overcome these problems, an efficient stacked deep transfer learning model is proposed that can efficiently distinguish between patients infected with Lyme (+) or infected with other infections. 2nd order edge-based color constancy is used as a preprocessing approach to reduce the impact of multisource light from images acquired under different setups. The AlexNet pretrained learning model is used for building the Lyme disease diagnosis model. To prevent overfitting, data augmentation techniques are also used to augment the dataset. In addition, 5-fold cross-validation is also used. Comparative analysis indicates that the proposed model outperforms the existing models in terms of accuracy, f-measure, sensitivity, specificity, and area under the curve.

COVID-19 is highly infectious and causes acute respiratory disease. Machine learning (ML) and deep learning (DL) models are vital in detecting disease from computerized chest tomography (CT) scans. The DL models outperformed the ML models. For COVID-19 detection from CT scan images, DL models are used as end-to-end models. Thus, the performance of the model is evaluated for the quality of the extracted feature and classification accuracy. There are four contributions included in this work. First, this research is motivated by studying the quality of the extracted feature from the DL by feeding these extracted to an ML model. In other words, we proposed comparing the end-to-end DL model performance against the approach of using DL for feature extraction and ML for the classification of COVID-19 CT scan images. Second, we proposed studying the effect of fusing extracted features from image descriptors, e.g., Scale-Invariant Feature Transform (SIFT), with extracted features from DL models. Third, we proposed a new Convolutional Neural Network (CNN) to be trained from scratch and then compared to the deep transfer learning on the same classification problem. Finally, we studied the performance gap between classic ML models against ensemble learning models. The proposed framework is evaluated using a CT dataset, where the obtained results are evaluated using five different metrics The obtained results revealed that using the proposed CNN model is better than using the well-known DL model for the purpose of feature extraction. Moreover, using a DL model for feature extraction and an ML model for the classification task achieved better results in comparison to using an end-to-end DL model for detecting COVID-19 CT scan images. Of note, the accuracy rate of the former method improved by using ensemble learning models instead of the classic ML models. The proposed method achieved the best accuracy rate of 99.39%.

Despite the continuous evolution and significant improvement of cybersecurity mechanisms, malware threats remain one of the most important concerns in cyberspace. Meanwhile, Android malware plays a big role in these ever-growing threats. In recent years, deep learning has become the dominant machine learning technique for malware detection and continues to make outstanding achievements. Deep graph representation learning is the task of embedding graph-structured data into a low-dimensional space using deep learning models. Recently, autoencoders have proven to be an effective way for deep representation learning. However, it is not straightforward to apply the idea of autoencoder to graph-structured data because of their irregular structure. In this paper, we present DroidMalGNN, a novel deep learning technique that combines autoencoders with graph neural networks (GNNs) to detect Android malware in an end-to-end manner. DroidMalGNN represents each Android application with an attributed function call graph (AFCG) that allows it to model complex relationships between data. For more efficiency, DroidMalGNN performs graph representation learning in a supervised manner where two autoencoders are trained with benign and malicious AFCGs separately. In this way, it generates two informative embedding vectors for each AFCG in a low-dimensional space and feeds them into a dense neural network to classify the AFCG as benign or malicious. Our experimental results show that DroidMalGNN can achieve good detection performance in terms of different evaluation measures.

Daily scale streamflow forecasting in multiple stream orders of Cauvery River, India: Application of advanced ensemble and deep learning models

AI-Driven molecule generation and bioactivity prediction: A multi-model approach combining VAE, graph and language-based neural networks.

Dermatological conditions are primarily prevalent in humans and are primarily caused by environmental and climatic fluctuations, as well as various other reasons. Timely identification is the most effective remedy to avert minor ailments from escalating into severe conditions. Diagnosing skin illnesses is consistently challenging for health practitioners. Presently, they rely on conventional methods, such as examining the condition of the skin. State-of-the-art technologies can enhance the accuracy of skin disease diagnosis by utilizing data-driven approaches. This paper presents a Computer Assisted Diagnosis (CAD) framework that has been developed to detect skin illnesses at an early stage. We suggest a computationally efficient and lightweight deep learning model that utilizes a CNN architecture. We then do thorough experiments to compare the performance of shallow and deep learning models. The CNN model under consideration consists of seven convolutional layers and has obtained an accuracy of 87.64% when applied to three distinct disease categories. The studies were conducted using the International Skin Imaging Collaboration (ISIC) dataset, which exclusively consists of dermoscopic images. This study enhances the field of skin disease diagnostics by utilizing state-of-the-art technology, attaining exceptional levels of accuracy, and striving for efficiency improvements. The unique features and future considerations of this technology create opportunities for additional advancements in the automated diagnosis of skin diseases and tailored treatment.

Accurate prediction of chemical reaction barrier heights is crucial, yet traditional quantum mechanical methods are computationally expensive, and existing deep learning models often rely on costly three-dimensional transition state geometries or struggle with out-of-distribution generalization. This work introduces ReactFormer, a novel deep learning framework designed to predict reaction barrier heights with high accuracy solely from two-dimensional molecular graphs of reactants, thus eliminating the need for explicit transition state information. ReactFormer employs a reaction-aware graph Transformer architecture, which includes multi-view reactant encoding and a unique Virtual Reaction Center Node, enabling it to effectively capture complex reaction features and implicitly infer transition state characteristics. Evaluated on the RDB7 dataset, ReactFormer achieves a Mean Absolute Error of 2.40 $\pm$ 0.12 kcal/mol on the random split, matching or even slightly surpassing the performance of three-dimensional dependent models. Furthermore, ReactFormer demonstrates significantly improved computational efficiency and robust generalization across various out-of-distribution scenarios, including splits based on molecular size, target barrier height, reaction core, and reactant scaffold. An ablation study confirms the critical contributions of its core components. ReactFormer represents a significant step towards efficient, accurate, and generalizable deep learning models for chemical reaction dynamics, fostering advancements in drug discovery, materials science, and catalysis.

Exponential growth in data rate demands has driven efforts to develop novel beamforming techniques for realizing massive multiple-input and multiple-output (MIMO) systems in sixth-generation (6G) terabits per second wireless communications. Existing beamforming techniques rely on conventional optimization algorithms that are too computationally expensive for real-time applications and require complex digital processing yet to be achieved for phased array antennas at terahertz frequencies. Here, we develop an intelligent and self-adaptive beamforming scheme enabled by deep reinforcement learning, which can predict the spatial phase profiles required to produce arbitrary desired radiation patterns in real-time. Our deep learning model adaptively trains an artificial neural network in real-time by comparing the input and predicted intensity patterns via automatic differentiation of the phase-to-intensity function. As a proof of concept, we experimentally demonstrate two-dimensional beamforming by spatially modulating broadband terahertz waves using silicon metasurfaces designed with the aid of the deep learning model. Our work offers an efficient and robust deep learning model for real-time self-adaptive beamforming to enable multi-user massive MIMO systems for 6G terahertz wireless communications, as well as intelligent metasurfaces for other terahertz applications in imaging and sensing.