Landscape of Neural Architecture Search across sensors: how much do they differ ?

With the rapid rise of neural architecture search, the ability to understand its complexity from the perspective of a search algorithm is desirable. Recently, Traor\'e et al. have proposed the framework of Fitness Landscape Footprint to help describe and compare neural architecture search problems. It attempts at describing why a search strategy might be successful, struggle or fail on a target task. Our study leverages this methodology in the context of searching across sensors, including sensor data fusion. In particular, we apply the Fitness Landscape Footprint to the real-world image classification problem of So2Sat LCZ42, in order to identify the most beneficial sensor to our neural network hyper-parameter optimization problem. From the perspective of distributions of fitness, our findings indicate a similar behaviour of the search space for all sensors: the longer the training time, the larger the overall fitness, and more flatness in the landscapes (less ruggedness and deviation). Regarding sensors, the better the fitness they enable (Sentinel-2), the better the search trajectories (smoother, higher persistence). Results also indicate very similar search behaviour for sensors that can be decently fitted by the search space (Sentinel-2 and fusion).

Tensor Recovery Based on Tensor Equivalent Minimax-Concave Penalty

Tensor recovery is an important problem in computer vision and machine learning. It usually uses the convex relaxation of tensor rank and $l_{0}$ norm, i.e., the nuclear norm and $l_{1}$ norm respectively, to solve the problem. It is well known that convex approximations produce biased estimators. In order to overcome this problem, a corresponding non-convex regularizer has been proposed to solve it. Inspired by matrix equivalent Minimax-Concave Penalty (EMCP), we propose and prove theorems of tensor equivalent Minimax-Concave Penalty (TEMCP). The tensor equivalent MCP (TEMCP) as a non-convex regularizer and the equivalent weighted tensor $\gamma$ norm (EWTGN) which can represent the low-rank part are obtained. Both of them can realize weight adaptive. At the same time, we propose two corresponding adaptive models for two classical tensor recovery problems, low-rank tensor completion (LRTC) and tensor robust principal component analysis (TRPCA), and the optimization algorithm is based on alternating direction multiplier (ADMM). This novel iterative adaptive algorithm can produce more accurate tensor recovery effect. For the tensor completion model, multispectral image (MSI), magnetic resonance imaging (MRI) and color video (CV) data sets are considered, while for the tensor robust principal component analysis model, hyperspectral image (HSI) denoising under gaussian noise plus salt and pepper noise is considered. The proposed algorithm is superior to the state-of-arts method, and the algorithm is guaranteed to meet the reduction and convergence through experiments.

Automatic Segmentation of Head and Neck Tumor: How Powerful Transformers Are?

Cancer is one of the leading causes of death worldwide, and head and neck (H&N) cancer is amongst the most prevalent types. Positron emission tomography and computed tomography are used to detect and segment the tumor region. Clinically, tumor segmentation is extensively time-consuming and prone to error. Machine learning, and deep learning in particular, can assist to automate this process, yielding results as accurate as the results of a clinician. In this research study, we develop a vision transformers-based method to automatically delineate H&N tumor, and compare its results to leading convolutional neural network (CNN)-based models. We use multi-modal data of CT and PET scans to do this task. We show that the selected transformer-based model can achieve results on a par with CNN-based ones. With cross validation, the model achieves a mean dice similarity coefficient of 0.736, mean precision of 0.766 and mean recall of 0.766. This is only 0.021 less than the 2020 competition winning model in terms of the DSC score. This indicates that the exploration of transformer-based models is a promising research area.

Language Models Explain Word Reading Times Better Than Empirical Predictability

Though there is a strong consensus that word length and frequency are the most important single-word features determining visual-orthographic access to the mental lexicon, there is less agreement as how to best capture syntactic and semantic factors. The traditional approach in cognitive reading research assumes that word predictability from sentence context is best captured by cloze completion probability (CCP) derived from human performance data. We review recent research suggesting that probabilistic language models provide deeper explanations for syntactic and semantic effects than CCP. Then we compare CCP with (1) Symbolic n-gram models consolidate syntactic and semantic short-range relations by computing the probability of a word to occur, given two preceding words. (2) Topic models rely on subsymbolic representations to capture long-range semantic similarity by word co-occurrence counts in documents. (3) In recurrent neural networks (RNNs), the subsymbolic units are trained to predict the next word, given all preceding words in the sentences. To examine lexical retrieval, these models were used to predict single fixation durations and gaze durations to capture rapidly successful and standard lexical access, and total viewing time to capture late semantic integration. The linear item-level analyses showed greater correlations of all language models with all eye-movement measures than CCP. Then we examined non-linear relations between the different types of predictability and the reading times using generalized additive models. N-gram and RNN probabilities of the present word more consistently predicted reading performance compared with topic models or CCP.

Efficient DNN Training with Knowledge-Guided Layer Freezing

Training deep neural networks (DNNs) is time-consuming. While most existing solutions try to overlap/schedule computation and communication for efficient training, this paper goes one step further by skipping computing and communication through DNN layer freezing. Our key insight is that the training progress of internal DNN layers differs significantly, and front layers often become well-trained much earlier than deep layers. To explore this, we first introduce the notion of training plasticity to quantify the training progress of internal DNN layers. Then we design KGT, a knowledge-guided DNN training system that employs semantic knowledge from a reference model to accurately evaluate individual layers' training plasticity and safely freeze the converged ones, saving their corresponding backward computation and communication. Our reference model is generated on the fly using quantization techniques and runs forward operations asynchronously on available CPUs to minimize the overhead. In addition, KGT caches the intermediate outputs of the frozen layers with prefetching to further skip the forward computation. Our implementation and testbed experiments with popular vision and language models show that KGT achieves 19%-43% training speedup w.r.t. the state-of-the-art without sacrificing accuracy.

WiSig: A Large-Scale WiFi Signal Dataset for Receiver and Channel Agnostic RF Fingerprinting

RF fingerprinting leverages circuit-level variability of transmitters to identify them using signals they send. Signals used for identification are impacted by a wireless channel and receiver circuitry, creating additional impairments that can confuse transmitter identification. Eliminating these impairments or just evaluating them, requires data captured over a prolonged period of time, using many spatially separated transmitters and receivers. In this paper, we present WiSig; a large scale WiFi dataset containing 10 million packets captured from 174 off-the-shelf WiFi transmitters and 41 USRP receivers over 4 captures spanning a month. WiSig is publicly available, not just as raw captures, but as conveniently pre-processed subsets of limited size, along with the scripts and examples. A preliminary evaluation performed using WiSig shows that changing receivers, or using signals captured on a different day can significantly degrade a trained classifier's performance. While capturing data over more days or more receivers limits the degradation, it is not always feasible and novel data-driven approaches are needed. WiSig provides the data to develop and evaluate these approaches towards channel and receiver agnostic transmitter fingerprinting.

Real-Time Context-aware Detection of Unsafe Events in Robot-Assisted Surgery

Cyber-physical systems for robotic surgery have enabled minimally invasive procedures with increased precision and shorter hospitalization. However, with increasing complexity and connectivity of software and major involvement of human operators in the supervision of surgical robots, there remain significant challenges in ensuring patient safety. This paper presents a safety monitoring system that, given the knowledge of the surgical task being performed by the surgeon, can detect safety-critical events in real-time. Our approach integrates a surgical gesture classifier that infers the operational context from the time-series kinematics data of the robot with a library of erroneous gesture classifiers that given a surgical gesture can detect unsafe events. Our experiments using data from two surgical platforms show that the proposed system can detect unsafe events caused by accidental or malicious faults within an average reaction time window of 1,693 milliseconds and F1 score of 0.88 and human errors within an average reaction time window of 57 milliseconds and F1 score of 0.76.

Safeguarding test signals for acoustic measurement using arbitrary sounds

We propose a simple method to measure acoustic responses using any sounds by converting them suitable for measurement. This method enables us to use music pieces for measuring acoustic conditions. It is advantageous to measure such conditions without annoying test sounds to listeners. In addition, applying the underlying idea of simultaneous measurement of multiple paths provides practically valuable features. For example, it is possible to measure deviations (temporally stable, random, and time-varying) and the impulse response while reproducing slightly modified contents under target conditions. The key idea of the proposed method is to add relatively small deterministic signals that sound like noise to the original sounds. We call the converted sounds safeguarded test signals.

Occupancy Information Ratio: Infinite-Horizon, Information-Directed, Parameterized Policy Search

We develop a new measure of the exploration/exploitation trade-off in infinite-horizon reinforcement learning problems called the occupancy information ratio (OIR), which is comprised of a ratio between the infinite-horizon average cost of a policy and the entropy of its long-term state occupancy measure. The OIR ensures that no matter how many trajectories an RL agent traverses or how well it learns to minimize cost, it maintains a healthy skepticism about its environment, in that it defines an optimal policy which induces a high-entropy occupancy measure. Different from earlier information ratio notions, OIR is amenable to direct policy search over parameterized families, and exhibits hidden quasiconcavity through invocation of the perspective transformation. This feature ensures that under appropriate policy parameterizations, the OIR optimization problem has no spurious stationary points, despite the overall problem's nonconvexity. We develop for the first time policy gradient and actor-critic algorithms for OIR optimization based upon a new entropy gradient theorem, and establish both asymptotic and non-asymptotic convergence results with global optimality guarantees. In experiments, these methodologies outperform several deep RL baselines in problems with sparse rewards, where many trajectories may be uninformative and skepticism about the environment is crucial to success.

Parkland Trauma Index of Mortality (PTIM): Real-time Predictive Model for PolyTrauma Patients

Vital signs and laboratory values are routinely used to guide clinical decision-making for polytrauma patients, such as the decision to use damage control techniques versus early definitive fracture fixation. Prior multivariate models have tried to predict mortality risk, but due to several limitations like one-time prediction at the time of admission, they have not proven clinically useful. There is a need for a dynamic model that captures evolving physiologic changes during patient's hospital course to trauma and resuscitation for mortality prediction. The Parkland Trauma Index of Mortality (PTIM) is a machine learning algorithm that uses electronic medical record (EMR) data to predict $48-$hour mortality during the first $72$ hours of hospitalization. The model updates every hour, evolving with the patient's physiologic response to trauma. Area under (AUC) the receiver-operator characteristic curve (ROC), sensitivity, specificity, positive (PPV) and negative predictive value (NPV), and positive and negative likelihood ratios (LR) were used to evaluate model performance. By evolving with the patient's physiologic response to trauma and relying only on EMR data, the PTIM overcomes many of the limitations of prior mortality risk models. It may be a useful tool to inform clinical decision-making for polytrauma patients early in their hospitalization.