We have embarked into a new phase in the field of AI/ML. On 29th June 2021, a novel and productive tool -- GitHub Copilot was developed by Microsoft subsidiary GitHub which has taken the internet by storm and has created a great deal of excitement and hype in the developer community. Though the tool isn't publicly available for everyone, there is a lot of buzz and excitement among people to gain access to the technical preview and really see if the is worth the hype that has been created around it! You might be wondering about the title of this blog . I am sure the title might have captivated your attention and brought you here.

Making machine learning operations easier to use, manage and organize for enterprises has always been the goal of the series of best practices known as MLOps. But while MLOps works well for the needed processes and commodity CPU-based infrastructure of traditional machine learning, it can come up short in being as useful for more complex deep learning workloads, which can be far larger and more demanding than traditional machine learning requirements. To fill this gap, New York-based startup, Spell, has launched what it calls a cloud-agnostic MLOps platform that is targeted to serve the more complex and unique needs of deep learning using the principles of MLOps used for machine learning. "With deep learning, there aren't a lot of options, because people are using their own tools," Tim Negris, the head of marketing for Spell, told EnterpriseAI. But using the company's newly-unveiled platform, enterprises can now more easily manage their deep learning model training, orchestration, monitoring, reporting, dashboarding and more, he said.

Background: Thyroid volumetry is crucial in diagnosis, treatment and monitoring of thyroid diseases. However, conventional thyroid volumetry with 2D ultrasound is highly operator-dependent. This study compares 2D ultrasound and tracked 3D ultrasound with an automatic thyroid segmentation based on a deep neural network regarding inter- and intraobserver variability, time and accuracy. Volume reference was MRI. Methods: 28 healthy volunteers were scanned with 2D and 3D ultrasound as well as by MRI. Three physicians (MD 1, 2, 3) with different levels of experience (6, 4 and 1 a) performed three 2D ultrasound and three tracked 3D ultrasound scans on each volunteer. In the 2D scans the thyroid lobe volumes were calculated with the ellipsoid formula. A convolutional deep neural network (CNN) segmented the 3D thyroid lobes automatically. On MRI (T1 VIBE sequence) the thyroid was manually segmented by an experienced medical doctor. Results: The CNN was trained to obtain a dice score of 0.94. The interobserver variability comparing two MDs showed mean differences for 2D and 3D respectively of 0.58 ml to 0.52 ml (MD1 vs. 2), -1.33 ml to -0.17 ml (MD1 vs. 3) and -1.89 ml to -0.70 ml (MD2 vs. 3). Paired samples t-tests showed significant differences in two comparisons for 2D and none for 3D. Intraobsever variability was similar for 2D and 3D ultrasound. Comparison of ultrasound volumes and MRI volumes by paired samples t-tests showed a significant difference for the 2D volumetry of all MDs, and no significant difference for 3D ultrasound. Acquisition time was significantly shorter for 3D ultrasound. Conclusion: Tracked 3D ultrasound combined with a CNN segmentation significantly reduces interobserver variability in thyroid volumetry and increases the accuracy of the measurements with shorter acquisition times.

Acoustic scene classification (ASC) aims to identify the type of scene (environment) in which a given audio signal is recorded. The log-mel feature and convolutional neural network (CNN) have recently become the most popular time-frequency (TF) feature representation and classifier in ASC. An audio signal recorded in a scene may include various sounds overlapping in time and frequency. The previous study suggests that separately considering the long-duration sounds and short-duration sounds in CNN may improve ASC accuracy. This study addresses the problem of the generalization ability of acoustic scene classifiers. In practice, acoustic scene signals' characteristics may be affected by various factors, such as the choice of recording devices and the change of recording locations. When an established ASC system predicts scene classes on audios recorded in unseen scenarios, its accuracy may drop significantly. The long-duration sounds not only contain domain-independent acoustic scene information, but also contain channel information determined by the recording conditions, which is prone to over-fitting. For a more robust ASC system, We propose a robust feature learning (RFL) framework to train the CNN. The RFL framework down-weights CNN learning specifically on long-duration sounds. The proposed method is to train an auxiliary classifier with only long-duration sound information as input. The auxiliary classifier is trained with an auxiliary loss function that assigns less learning weight to poorly classified examples than the standard cross-entropy loss. The experimental results show that the proposed RFL framework can obtain a more robust acoustic scene classifier towards unseen devices and cities.

Errors in measurements are key to weighting the value of data, but are often neglected in Machine Learning (ML). We show how Convolutional Neural Networks (CNNs) are able to learn about the context and patterns of signal and noise, leading to improvements in the performance of classification methods. We construct a model whereby two classes of objects follow an underlying Gaussian distribution, and where the features (the input data) have varying, but known, levels of noise. This model mimics the nature of scientific data sets, where the noises arise as realizations of some random processes whose underlying distributions are known. The classification of these objects can then be performed using standard statistical techniques (e.g., least-squares minimization or Markov-Chain Monte Carlo), as well as ML techniques. This allows us to take advantage of a maximum likelihood approach to object classification, and to measure the amount by which the ML methods are incorporating the information in the input data uncertainties. We show that, when each data point is subject to different levels of noise (i.e., noises with different distribution functions), that information can be learned by the CNNs, raising the ML performance to at least the same level of the least-squares method -- and sometimes even surpassing it. Furthermore, we show that, with varying noise levels, the confidence of the ML classifiers serves as a proxy for the underlying cumulative distribution function, but only if the information about specific input data uncertainties is provided to the CNNs.

We propose a quantum algorithm for sampling from a solution of stochastic differential equations (SDEs). Using differentiable quantum circuits (DQCs) with a feature map encoding of latent variables, we represent the quantile function for an underlying probability distribution and extract samples as DQC expectation values. Using quantile mechanics we propagate the system in time, thereby allowing for time-series generation. We test the method by simulating the Ornstein-Uhlenbeck process and sampling at times different from the initial point, as required in financial analysis and dataset augmentation. Additionally, we analyse continuous quantum generative adversarial networks (qGANs), and show that they represent quantile functions with a modified (reordered) shape that impedes their efficient time-propagation. Our results shed light on the connection between quantum quantile mechanics (QQM) and qGANs for SDE-based distributions, and point the importance of differential constraints for model training, analogously with the recent success of physics informed neural networks.

Different from visible cameras which record intensity images frame by frame, the biologically inspired event camera produces a stream of asynchronous and sparse events with much lower latency. In practice, the visible cameras can better perceive texture details and slow motion, while event cameras can be free from motion blurs and have a larger dynamic range which enables them to work well under fast motion and low illumination. Therefore, the two sensors can cooperate with each other to achieve more reliable object tracking. In this work, we propose a large-scale Visible-Event benchmark (termed VisEvent) due to the lack of a realistic and scaled dataset for this task. Our dataset consists of 820 video pairs captured under low illumination, high speed, and background clutter scenarios, and it is divided into a training and a testing subset, each of which contains 500 and 320 videos, respectively. Based on VisEvent, we transform the event flows into event images and construct more than 30 baseline methods by extending current single-modality trackers into dual-modality versions. More importantly, we further build a simple but effective tracking algorithm by proposing a cross-modality transformer, to achieve more effective feature fusion between visible and event data. Extensive experiments on the proposed VisEvent dataset, and two simulated datasets (i.e., OTB-DVS and VOT-DVS), validated the effectiveness of our model. The dataset and source code will be available at our project page: \url{https://sites.google.com/view/viseventtrack/}.

Vision-and-language(V&L) models take image and text as input and learn to capture the associations between them. Prior studies show that pre-trained V&L models can significantly improve the model performance for downstream tasks such as Visual Question Answering (VQA). However, V&L models are less effective when applied in the medical domain (e.g., on X-ray images and clinical notes) due to the domain gap. In this paper, we investigate the challenges of applying pre-trained V&L models in medical applications. In particular, we identify that the visual representation in general V&L models is not suitable for processing medical data. To overcome this limitation, we propose BERTHop, a transformer-based model based on PixelHop++ and VisualBERT, for better capturing the associations between the two modalities. Experiments on the OpenI dataset, a commonly used thoracic disease diagnosis benchmark, show that BERTHop achieves an average Area Under the Curve (AUC) of 98.12% which is 1.62% higher than state-of-the-art (SOTA) while it is trained on a 9 times smaller dataset.

Language-guided robots performing home and office tasks must navigate in and interact with the world. Grounding language instructions against visual observations and actions to take in an environment is an open challenge. We present Embodied BERT (EmBERT), a transformer-based model which can attend to high-dimensional, multi-modal inputs across long temporal horizons for language-conditioned task completion. Additionally, we bridge the gap between successful object-centric navigation models used for non-interactive agents and the language-guided visual task completion benchmark, ALFRED, by introducing object navigation targets for EmBERT training. We achieve competitive performance on the ALFRED benchmark, and EmBERT marks the first transformer-based model to successfully handle the long-horizon, dense, multi-modal histories of ALFRED, and the first ALFRED model to utilize object-centric navigation targets.

Attempting to fully exploit the rich information of topological structure and node features for attributed graph, we introduce self-supervised learning mechanism to graph representation learning and propose a novel Self-supervised Consensus Representation Learning (SCRL) framework. In contrast to most existing works that only explore one graph, our proposed SCRL method treats graph from two perspectives: topology graph and feature graph. We argue that their embeddings should share some common information, which could serve as a supervisory signal. Specifically, we construct the feature graph of node features via k-nearest neighbor algorithm. Then graph convolutional network (GCN) encoders extract features from two graphs respectively. Self-supervised loss is designed to maximize the agreement of the embeddings of the same node in the topology graph and the feature graph. Extensive experiments on real citation networks and social networks demonstrate the superiority of our proposed SCRL over the state-of-the-art methods on semi-supervised node classification task. Meanwhile, compared with its main competitors, SCRL is rather efficient.