Historical handwritten documents guard an important part of human knowledge only within reach of a few scholars and experts. Recent developments in machine learning and handwriting research have the potential of rendering this information accessible and searchable to a larger audience. To this end, we investigate an end-to-end inference approach without text localization which takes a handwritten page and transcribes its full text. No explicit character, word or line segmentation is involved in inference which is why we call this approach "segmentation free". We explore its robustness and accuracy compared to a line-by-line segmented approach based on the IAM, RODRIGO and ScribbleLens corpora, in three languages with handwriting styles spanning 400 years. We concentrate on model types and sizes which can be deployed on a hand-held or embedded device. We conclude that a whole page inference approach without text localization and segmentation is competitive.

Recently, Tensor Ring Networks (TRNs) have been applied in deep networks, achieving remarkable successes in compression ratio and accuracy. Although highly related to the performance of TRNs, rank is seldom studied in previous works and usually set to equal in experiments. Meanwhile, there is not any heuristic method to choose the rank, and an enumerating way to find appropriate rank is extremely time-consuming. Interestingly, we discover that part of the rank elements is sensitive and usually aggregate in a certain region, namely an interest region. Therefore, based on the above phenomenon, we propose a novel progressive genetic algorithm named Progressively Searching Tensor Ring Network Search (PSTRN), which has the ability to find optimal rank precisely and efficiently. Through the evolutionary phase and progressive phase, PSTRN can converge to the interest region quickly and harvest good performance. Experimental results show that PSTRN can significantly reduce the complexity of seeking rank, compared with the enumerating method. Furthermore, our method is validated on public benchmarks like MNIST, CIFAR10/100 and HMDB51, achieving state-of-the-art performance.

Bayesian predictive coding is a putative neuromorphic method for acquiring higher-level neural representations to account for sensory input. Although originating in the neuroscience community, there are also efforts in the machine learning community to study these models. This paper reviews some of the more well known models. Our review analyzes module connectivity and patterns of information transfer, seeking to find general principles used across the models. We also survey some recent attempts to cast these models within a deep learning framework. A defining feature of Bayesian predictive coding is that it uses top-down, reconstructive mechanisms to predict incoming sensory inputs or their lower-level representations. Discrepancies between the predicted and the actual inputs, known as prediction errors, then give rise to future learning that refines and improves the predictive accuracy of learned higher-level representations. Predictive coding models intended to describe computations in the neocortex emerged prior to the development of deep learning and used a communication structure between modules that we name the Rao-Ballard protocol. This protocol was derived from a Bayesian generative model with some rather strong statistical assumptions. The RB protocol provides a rubric to assess the fidelity of deep learning models that claim to implement predictive coding.

EXplainable AI (XAI) methods have been proposed to interpret how a deep neural network predicts inputs through model saliency explanations that highlight the parts of the inputs deemed important to arrive a decision at a specific target. However, it remains challenging to quantify correctness of their interpretability as current evaluation approaches either require subjective input from humans or incur high computation cost with automated evaluation. In this paper, we propose backdoor trigger patterns--hidden malicious functionalities that cause misclassification--to automate the evaluation of saliency explanations. Our key observation is that triggers provide ground truth for inputs to evaluate whether the regions identified by an XAI method are truly relevant to its output. Since backdoor triggers are the most important features that cause deliberate misclassification, a robust XAI method should reveal their presence at inference time. We introduce three complementary metrics for systematic evaluation of explanations that an XAI method generates and evaluate seven state-of-the-art model-free and model-specific posthoc methods through 36 models trojaned with specifically crafted triggers using color, shape, texture, location, and size. We discovered six methods that use local explanation and feature relevance fail to completely highlight trigger regions, and only a model-free approach can uncover the entire trigger region.

However, the performance of AL heuristics depends on the structure of the underlying classifier model and the data. We propose an imitation learning scheme that imitates the selection of the best expert heuristic at each stage of the AL cycle in a batch-mode pool-based setting. With multiple AL heuristics as experts, the policy is able to reflect the choices of the best AL heuristics given the current state of the AL process. Our experiment on well-known datasets show that we both outperform state of the art imitation learners and heuristics. The high performance of deep learning on various tasks from computer vision (Voulodimos et al., 2018) to natural language processing (NLP) (Barrault et al., 2019) also comes with disadvantages. One of their main drawbacks is the large amount of labeled training data they require. Obtaining such data is expensive and time-consuming and often requires domain expertise (Löffler et al., 2020). Active Learning (AL) is an iterative process where during every iteration an oracle (e.g. a human) is asked to label the most informative unlabeled data sample(s). In pool-based AL all data samples are available (while most of them are unlabeled). In batch-mode pool-based AL, we select unlabeled data samples from the pool in acquisition batches greater than 1. Batch-mode AL decreases the number of AL iterations required and makes it easier for an oracle to label the data samples (Settles, 2009).

Firefighting is a dynamic activity, in which numerous operations occur simultaneously. Maintaining situational awareness (i.e., knowledge of current conditions and activities at the scene) is critical to the accurate decision-making necessary for the safe and successful navigation of a fire environment by firefighters. Conversely, the disorientation caused by hazards such as smoke and extreme heat can lead to injury or even fatality. This research implements recent advancements in technology such as deep learning, point cloud and thermal imaging, and augmented reality platforms to improve a firefighter's situational awareness and scene navigation through improved interpretation of that scene. We have designed and built a prototype embedded system that can leverage data streamed from cameras built into a firefighter's personal protective equipment (PPE) to capture thermal, RGB color, and depth imagery and then deploy already developed deep learning models to analyze the input data in real time. The embedded system analyzes and returns the processed images via wireless streaming, where they can be viewed remotely and relayed back to the firefighter using an augmented reality platform that visualizes the results of the analyzed inputs and draws the firefighter's attention to objects of interest, such as doors and windows otherwise invisible through smoke and flames.

We develop FedCluster--a novel federated learning framework with improved optimization efficiency, and investigate its theoretical convergence properties. The FedCluster groups the devices into multiple clusters that perform federated learning cyclically in each learning round. Therefore, each learning round of FedCluster consists of multiple cycles of meta-update that boost the overall convergence. In nonconvex optimization, we show that FedCluster with the devices implementing the local {stochastic gradient descent (SGD)} algorithm achieves a faster convergence rate than the conventional {federated averaging (FedAvg)} algorithm in the presence of device-level data heterogeneity. We conduct experiments on deep learning applications and demonstrate that FedCluster converges significantly faster than the conventional federated learning under diverse levels of device-level data heterogeneity for a variety of local optimizers.

Learning in deep neural networks (DNNs) is implemented through minimizing a highly non-convex loss function, typically by a stochastic gradient descent (SGD) method. This learning process can effectively find good wide minima without being trapped in poor local ones. We present a novel account of how such effective deep learning emerges through the interactions of the SGD and the geometrical structure of the loss landscape. Rather than being a normal diffusion process (i.e. Brownian motion) as often assumed, we find that the SGD exhibits rich, complex dynamics when navigating through the loss landscape; initially, the SGD exhibits anomalous superdiffusion, which attenuates gradually and changes to subdiffusion at long times when the solution is reached. Such learning dynamics happen ubiquitously in different DNNs such as ResNet and VGG-like networks and are insensitive to batch size and learning rate. The anomalous superdiffusion process during the initial learning phase indicates that the motion of SGD along the loss landscape possesses intermittent, big jumps; this non-equilibrium property enables the SGD to escape from sharp local minima. By adapting the methods developed for studying energy landscapes in complex physical systems, we find that such superdiffusive learning dynamics are due to the interactions of the SGD and the fractal-like structure of the loss landscape. We further develop a simple model to demonstrate the mechanistic role of the fractal loss landscape in enabling the SGD to effectively find global minima. Our results thus reveal the effectiveness of deep learning from a novel perspective and have implications for designing efficient deep neural networks.

A vital problem in solving classification or regression problem is to apply feature engineering and variable selection on data before fed into models.One of a most popular feature engineering method is to discretisize continous variable with some cutting points,which is refered to as bining processing.Good cutting points are important for improving model's ability, because wonderful bining may ignore some noisy variance in continous variable range and keep useful leveled information with good ordered encodings.However, to our best knowledge a majority of cutting point selection is done via researchers domain knownledge or some naive methods like equal-width cutting or equal-frequency cutting.In this paper we propose an end-to-end supervised cutting point selection method based on group and fused lasso along with the automatically variable selection effect.We name our method \textbf{ABM}(automatic bining machine). We firstly cut each variable range into fine grid bins and train model with our group and group fused lasso regularization on each successive bins.It is a method that integrates feature engineering,variable selection and model training simultanously.And one more inspiring thing is that the method is flexible such that it can be taken into a bunch of loss function based model including deep neural networks.We have also implemented the method in R and open the source code to other researchers.A Python version will also meet the community in days.

Protein secondary structure is crucial to creating an information bridge between the primary and tertiary (3D) structures. Precise prediction of eight-state protein secondary structure (PSS) has significantly utilized in the structural and functional analysis of proteins in bioinformatics. Deep learning techniques have been recently applied in this research area and raised the eight-state (Q8) protein secondary structure prediction accuracy remarkably. Nevertheless, from a theoretical standpoint, there are still lots of rooms for improvement, specifically in the eight-state PSS prediction. In this study, we have presented a new deep convolutional neural network (DCNN), namely PS8-Net, to enhance the accuracy of eight-class PSS prediction. The input of this architecture is a carefully constructed feature matrix from the proteins sequence features and profile features. We introduce a new PS8 module in the network, which is applied with skip connection to extracting the long-term inter-dependencies from higher layers, obtaining local contexts in earlier layers, and achieving global information during secondary structure prediction. Our proposed PS8-Net achieves 76.89%, 71.94%, 76.86%, and 75.26% Q8 accuracy respectively on benchmark CullPdb6133, CB513, CASP10, and CASP11 datasets. This architecture enables the efficient processing of local and global interdependencies between amino acids to make an accurate prediction of each class. To the best of our knowledge, PS8-Net experiment results demonstrate that it outperforms all the state-of-the-art methods on the aforementioned benchmark datasets.