We present the first deep learning model for the analysis of intracytoplasmic sperm injection (ICSI) procedures. Using a dataset of ICSI procedure videos, we train a deep neural network to segment key objects in the videos achieving a mean IoU of 0.962, and to localize the needle tip achieving a mean pixel error of 3.793 pixels at 14 FPS on a single GPU. We further analyze the variation between the dataset's human annotators and find the model's performance to be comparable to human experts.

Using machine learning, we explore the utility of various deep neural networks (NN) when applied to high harmonic generation (HHG) scenarios. First, we train the NNs to predict the time-dependent dipole and spectra of HHG emission from reduced-dimensionality models of di- and triatomic systems based of on sets of randomly generated parameters (laser pulse intensity, internuclear distance, and molecular orientation). These networks, once trained, are useful tools to rapidly generate the HHG spectra of our systems. Similarly, we have trained the NNs to solve the inverse problem - to determine the molecular parameters based on HHG spectra or dipole acceleration data. These types of networks could then be used as spectroscopic tools to invert HHG spectra in order to recover the underlying physical parameters of a system. Next, we demonstrate that transfer learning can be applied to our networks to expand the range of applicability of the networks with only a small number of new test cases added to our training sets. Finally, we demonstrate NNs that can be used to classify molecules by type: di- or triatomic, symmetric or asymmetric, wherein we can even rely on fairly simple fully connected neural networks. With outlooks toward training with experimental data, these NN topologies offer a novel set of spectroscopic tools that could be incorporated into HHG experiments.

Respiratory auscultation can help healthcare professionals detect abnormal respiratory conditions if adventitious lung sounds are heard. The state-of-the-art artificial intelligence technologies based on deep learning show great potential in the development of automated respiratory sound analysis. To train a deep learning-based model, a huge number of accurate labels of normal breath sounds and adventitious sounds are needed. In this paper, we demonstrate the work of developing a respiratory sound labeling software to help annotators identify and label the inhalation, exhalation, and adventitious respiratory sound more accurately and quickly. Our labeling software integrates six features from MATLAB Audio Labeler, and one commercial audio editor, RX7. As of October, 2019, we have labeled 9,765 15-second-long audio files of breathing lung sounds, and accrued 34,095 inhalation labels,18,349 exhalation labels, 13,883 continuous adventitious sounds (CASs) labels and 15,606 discontinuous adventitious sounds (DASs) labels, which are significantly larger than previously published studies. The trained convolutional recurrent neural networks based on these labels showed good performance with F1-scores of 86.0% on inhalation event detection, 51.6% on CASs event detection and 71.4% on DASs event detection. In conclusion, our results show that our proposed respiratory sound labeling software could easily pre-define a label, perform one-click labeling, and overall facilitate the process of accurately labeling. This software helps develop deep learning-based models that require a huge amount of labeled acoustic data.

Industrial Internet of Things (IIoT) lays a new paradigm for the concept of Industry 4.0 and paves an insight for new industrial era. Nowadays smart machines and smart factories use machine learning/deep learning based models for incurring intelligence. However, storing and communicating the data to the cloud and end device leads to issues in preserving privacy. In order to address this issue, federated learning (FL) technology is implemented in IIoT by the researchers nowadays to provide safe, accurate, robust and unbiased models. Integrating FL in IIoT ensures that no local sensitive data is exchanged, as the distribution of learning models over the edge devices has become more common with FL. Therefore, only the encrypted notifications and parameters are communicated to the central server. In this paper, we provide a thorough overview on integrating FL with IIoT in terms of privacy, resource and data management. The survey starts by articulating IIoT characteristics and fundamentals of distributive and FL. The motivation behind integrating IIoT and FL for achieving data privacy preservation and on-device learning are summarized. Then we discuss the potential of using machine learning, deep learning and blockchain techniques for FL in secure IIoT. Further we analyze and summarize the ways to handle the heterogeneous and huge data. Comprehensive background on data and resource management are then presented, followed by applications of IIoT with FL in healthcare and automobile industry. Finally, we shed light on challenges, some possible solutions and potential directions for future research.

Machine Learning (ML) techniques have been rapidly adopted by smart Cyber-Physical Systems (CPS) and Internet-of-Things (IoT) due to their powerful decision-making capabilities. However, they are vulnerable to various security and reliability threats, at both hardware and software levels, that compromise their accuracy. These threats get aggravated in emerging edge ML devices that have stringent constraints in terms of resources (e.g., compute, memory, power/energy), and that therefore cannot employ costly security and reliability measures. Security, reliability, and vulnerability mitigation techniques span from network security measures to hardware protection, with an increased interest towards formal verification of trained ML models. This paper summarizes the prominent vulnerabilities of modern ML systems, highlights successful defenses and mitigation techniques against these vulnerabilities, both at the cloud (i.e., during the ML training phase) and edge (i.e., during the ML inference stage), discusses the implications of a resource-constrained design on the reliability and security of the system, identifies verification methodologies to ensure correct system behavior, and describes open research challenges for building secure and reliable ML systems at both the edge and the cloud.

One of the major optimizations employed in deep learning frameworks is graph rewriting. Production frameworks rely on heuristics to decide if rewrite rules should be applied and in which order. Prior research has shown that one can discover more optimal tensor computation graphs if we search for a better sequence of substitutions instead of relying on heuristics. However, we observe that existing approaches for tensor graph superoptimization both in production and research frameworks apply substitutions in a sequential manner. Such sequential search methods are sensitive to the order in which the substitutions are applied and often only explore a small fragment of the exponential space of equivalent graphs. This paper presents a novel technique for tensor graph superoptimization that employs equality saturation to apply all possible substitutions at once. We show that our approach can find optimized graphs with up to 16% speedup over state-of-the-art, while spending on average 48x less time optimizing.

Embedding static graphs in low-dimensional vector spaces plays a key role in network analytics and inference, supporting applications like node classification, link prediction, and graph visualization. However, many real-world networks present dynamic behavior, including topological evolution, feature evolution, and diffusion. Therefore, several methods for embedding dynamic graphs have been proposed to learn network representations over time, facing novel challenges, such as time-domain modeling, temporal features to be captured, and the temporal granularity to be embedded. In this survey, we overview dynamic graph embedding, discussing its fundamentals and the recent advances developed so far. We introduce the formal definition of dynamic graph embedding, focusing on the problem setting and introducing a novel taxonomy for dynamic graph embedding input and output. We further explore different dynamic behaviors that may be encompassed by embeddings, classifying by topological evolution, feature evolution, and processes on networks. Afterward, we describe existing techniques and propose a taxonomy for dynamic graph embedding techniques based on algorithmic approaches, from matrix and tensor factorization to deep learning, random walks, and temporal point processes. We also elucidate main applications, including dynamic link prediction, anomaly detection, and diffusion prediction, and we further state some promising research directions in the area.

Astounding results from transformer models on natural language tasks have intrigued the vision community to study their application to computer vision problems. This has led to exciting progress on a number of tasks while requiring minimal inductive biases in the model design. This survey aims to provide a comprehensive overview of the transformer models in the computer vision discipline and assumes little to no prior background in the field. We start with an introduction to fundamental concepts behind the success of transformer models i.e., self-supervision and self-attention. Transformer architectures leverage self-attention mechanisms to encode long-range dependencies in the input domain which makes them highly expressive. Since they assume minimal prior knowledge about the structure of the problem, self-supervision using pretext tasks is applied to pre-train transformer models on large-scale (unlabelled) datasets. The learned representations are then fine-tuned on the downstream tasks, typically leading to excellent performance due to the generalization and expressivity of encoded features. We cover extensive applications of transformers in vision including popular recognition tasks (e.g., image classification, object detection, action recognition, and segmentation), generative modeling, multi-modal tasks (e.g., visual-question answering and visual reasoning), video processing (e.g., activity recognition, video forecasting), low-level vision (e.g., image super-resolution and colorization) and 3D analysis (e.g., point cloud classification and segmentation). We compare the respective advantages and limitations of popular techniques both in terms of architectural design and their experimental value. Finally, we provide an analysis on open research directions and possible future works.

Following the recent initiatives for the democratization of AI, deep fake generators have become increasingly popular and accessible, causing dystopian scenarios towards social erosion of trust. A particular domain, such as biological signals, attracted attention towards detection methods that are capable of exploiting authenticity signatures in real videos that are not yet faked by generative approaches. In this paper, we first propose several prominent eye and gaze features that deep fakes exhibit differently. Second, we compile those features into signatures and analyze and compare those of real and fake videos, formulating geometric, visual, metric, temporal, and spectral variations. Third, we generalize this formulation to deep fake detection problem by a deep neural network, to classify any video in the wild as fake or real. We evaluate our approach on several deep fake datasets, achieving 89.79\% accuracy on FaceForensics++, 80.0\% on Deep Fakes (in the wild), and 88.35\% on CelebDF datasets. We conduct ablation studies involving different features, architectures, sequence durations, and post-processing artifacts. Our analysis concludes with 6.29\% improved accuracy over complex network architectures without the proposed gaze signatures.

We present a high-bandwidth, lightweight, and nonlinear output tracking technique for soft actuators that combines parsimonious recursive layers for forward output predictions and online optimization using Newton-Raphson. This technique allows for reduced model sizes and increased control loop frequencies when compared with conventional RNN models. Experimental results of this controller prototype on a single soft actuator with soft positional sensors indicate effective tracking of referenced spatial trajectories and rejection of mechanical and electromagnetic disturbances. These are evidenced by root mean squared path tracking errors (RMSE) of 1.8mm using a fully connected (FC) substructure, 1.62mm using a gated recurrent unit (GRU) and 2.11mm using a long short term memory (LSTM) unit, all averaged over three tasks. Among these models, the highest flash memory requirement is 2.22kB enabling co-location of controller and actuator.