The nifty app CamFind has come a long way with its artificial intelligence. It uses image recognition to identify an object when you point your smartphone camera at it. But back in 2015 its algorithms were less advanced: The app mostly used contract workers in the Philippines to quickly type what they saw through a user's phone camera, CamFind's co-founder confirmed to me recently. You would not have guessed that from a press release it put out that year which touted industry-leading "deep learning technology," but did not mention any human labellers. The practice of hiding human input in AI systems still remains an open secret among those who work in machine learning and AI.

But the story is bigger than just using quantum computers to tackle machine learning problems. Quantum circuits are differentiable, and a quantum computer itself can compute the change in control parameters needed to become better at a given task. Differentiable programming is the very basis of deep learning, implemented in software libraries such as TensorFlow and PyTorch. Differentiable programming is more than deep learning: it is a programming paradigm where the algorithms are not hand-coded, but learned. Similarly, the idea of training quantum computers is larger than quantum machine learning.

There is a worldwide community that collects "reborn dolls." These dolls look almost like real babies. They help some collectors cope with the loss of a child. For others, it fulfills their sense of self image. And yet others just see them as a quirky hobby.

A deep learning framework is a software package used by researchers and data scientists to design and train deep learning models. The idea with these frameworks is to allow people to train their models without digging into the algorithms underlying deep learning, neural networks, and machine learning. These frameworks offer building blocks for designing, training, and validating models through a high-level programming interface. Widely used deep learning frameworks such as PyTorch, TensorFlow, MXNet, and others can also use GPU-accelerated libraries such as cuDNN and NCCL to deliver high-performance multi-GPU accelerated training. An open-source software library created by Google, TensorFlow is a popular tool for machine learning, especially for training deep neural networks.

To develop an algorithm to classify postcontrast T1-weighted MRI scans by tumor classes (high-grade glioma, low-grade glioma [LGG], brain metastasis, meningioma, pituitary adenoma, and acoustic neuroma) and a healthy tissue (HLTH) class. In this retrospective study, preoperative postcontrast T1-weighted MR scans from four publicly available datasets--the Brain Tumor Image Segmentation dataset (n 378), the LGG-1p19q dataset (n 145), The Cancer Genome Atlas Glioblastoma Multiforme dataset (n 141), and The Cancer Genome Atlas Low Grade Glioma dataset (n 68)--and an internal clinical dataset (n 1373) were used. In all, a total of 2105 images were split into a training dataset (n 1396), an internal test set (n 361), and an external test dataset (n 348). A convolutional neural network was trained to classify the tumor type and to discriminate between images depicting HLTH and images depicting tumors. The performance of the model was evaluated by using cross-validation, internal testing, and external testing.

To efficiently navigate their surrounding environments and complete missions, unmanned aerial systems (UASs) should be able to detect multiple objects in their surroundings and track their movements over time. So far, however, enabling multi-object tracking in unmanned aerial vehicles has proved to be fairly challenging. Researchers at Lockheed Martin AI Center have recently developed a new deep learning technique that could allow UASs to track multiple objects in their surroundings. Their technique, presented in a paper pre-published on arXiv, could aid the development of better performing and more responsive autonomous flying systems. "We present a robust object tracking architecture aimed to accommodate for the noise in real-time situations," the researchers wrote in their paper.

Deep learning techniques have been increasingly applied to the natural sciences, e.g., for property prediction and optimization or material discovery. A fundamental ingredient of such approaches is the vast quantity of labelled data needed to train the model; this poses severe challenges in data-scarce settings where obtaining labels requires substantial computational or labor resources. Here, we introduce surrogate- and invariance-boosted contrastive learning (SIB-CL), a deep learning framework which incorporates three ``inexpensive'' and easily obtainable auxiliary information sources to overcome data scarcity. Specifically, these are: 1)~abundant unlabeled data, 2)~prior knowledge of symmetries or invariances and 3)~surrogate data obtained at near-zero cost. We demonstrate SIB-CL's effectiveness and generality on various scientific problems, e.g., predicting the density-of-states of 2D photonic crystals and solving the 3D time-independent Schrodinger equation. SIB-CL consistently results in orders of magnitude reduction in the number of labels needed to achieve the same network accuracies.

Vacuum Insulated Glazing (VIG) is a highly thermally insulating window technology, which boasts an extremely thin profile and lower weight as compared to gas-filled insulated glazing units of equivalent performance. The VIG is a double-pane configuration with a submillimeter vacuum gap between the panes and therefore under constant atmospheric pressure over their service life. Small pillars are positioned between the panes to maintain the gap, which can damage the glass reducing the lifetime of the VIG unit. To efficiently assess any surface damage on the glass, an automated damage detection system is highly desirable. For the purpose of classifying the damage, we have developed, trained, and tested a deep learning computer vision system using convolutional neural networks. The classification model flawlessly classified the test dataset with an area under the curve (AUC) for the receiver operating characteristic (ROC) of 100%. We have automatically cropped the images down to their relevant information by using Faster-RCNN to locate the position of the pillars. We employ the state-of-the-art methods Grad-CAM and Score-CAM of explainable Artificial Intelligence (XAI) to provide an understanding of the internal mechanisms and were able to show that our classifier outperforms ResNet50V2 for identification of crack locations and geometry. The proposed methods can therefore be used to detect systematic defects even without large amounts of training data. Further analyses of our model's predictive capabilities demonstrates its superiority over state-of-the-art models (ResNet50V2, ResNet101V2 and ResNet152V2) in terms of convergence speed, accuracy, precision at 100% recall and AUC for ROC.

Single-cell sequencing has a significant role to explore biological processes such as embryonic development, cancer evolution, and cell differentiation. These biological properties can be presented by a two-dimensional scatter plot. However, single-cell sequencing data generally has very high dimensionality. Therefore, dimensionality reduction should be used to process the high dimensional sequencing data for 2D visualization and subsequent biological analysis. The traditional dimensionality reduction methods, which do not consider the structure characteristics of single-cell sequencing data, are difficult to reveal the data structure in the 2D representation. In this paper, we develop a 2D feature representation method based on graph convolutional networks (GCN) for the visualization of single-cell data, termed single-cell sequencing graph embedding networks (SGEN). This method constructs the graph by the similarity relationship between cells and adopts GCN to analyze the neighbor embedding information of samples, which makes the similar cell closer to each other on the 2D scatter plot. The results show SGEN achieves obvious 2D distribution and preserves the high-dimensional relationship of different cells. Meanwhile, similar cell clusters have spatial continuity rather than relying heavily on random initialization, which can reflect the trajectory of cell development in this scatter plot.

Improving the training and inference performance of graph neural networks (GNNs) is faced with a challenge uncommon in general neural networks: creating mini-batches requires a lot of computation and data movement due to the exponential growth of multi-hop graph neighborhoods along network layers. Such a unique challenge gives rise to a diverse set of system design choices. We argue in favor of performing mini-batch training with neighborhood sampling in a distributed multi-GPU environment, under which we identify major performance bottlenecks hitherto under-explored by developers: mini-batch preparation and transfer. We present a sequence of improvements to mitigate these bottlenecks, including a performance-engineered neighborhood sampler, a shared-memory parallelization strategy, and the pipelining of batch transfer with GPU computation. We also conduct an empirical analysis that supports the use of sampling for inference, showing that test accuracies are not materially compromised. Such an observation unifies training and inference, simplifying model implementation. We report comprehensive experimental results with several benchmark data sets and GNN architectures, including a demonstration that, for the ogbn-papers100M data set, our system SALIENT achieves a speedup of 3x over a standard PyTorch-Geometric implementation with a single GPU and a further 8x parallel speedup with 16 GPUs. Therein, training a 3-layer GraphSAGE model with sampling fanout (15, 10, 5) takes 2.0 seconds per epoch and inference with fanout (20, 20, 20) takes 2.4 seconds, attaining test accuracy 64.58%.