Depression is a common mental disorder. Automatic depression detection tools using speech, enabled by machine learning, help early screening of depression. This paper addresses two limitations that may hinder the clinical implementations of such tools: noise resulting from segment-level labelling and a lack of model interpretability. We propose a bi-modal speech-level transformer to avoid segment-level labelling and introduce a hierarchical interpretation approach to provide both speech-level and sentence-level interpretations, based on gradient-weighted attention maps derived from all attention layers to track interactions between input features. We show that the proposed model outperforms a model that learns at a segment level ($p$=0.854, $r$=0.947, $F1$=0.947 compared to $p$=0.732, $r$=0.808, $F1$=0.768). For model interpretation, using one true positive sample, we show which sentences within a given speech are most relevant to depression detection; and which text tokens and Mel-spectrogram regions within these sentences are most relevant to depression detection. These interpretations allow clinicians to verify the validity of predictions made by depression detection tools, promoting their clinical implementations.
相關內容
A Retrieval-Augmented Language Model (RALM) augments a generative language model by retrieving context-specific knowledge from an external database. This strategy facilitates impressive text generation quality even with smaller models, thus reducing orders of magnitude of computational demands. However, RALMs introduce unique system design challenges due to (a) the diverse workload characteristics between LM inference and retrieval and (b) the various system requirements and bottlenecks for different RALM configurations such as model sizes, database sizes, and retrieval frequencies. We propose Chameleon, a heterogeneous accelerator system that integrates both LM and retrieval accelerators in a disaggregated architecture. The heterogeneity ensures efficient acceleration of both LM inference and retrieval, while the accelerator disaggregation enables the system to independently scale both types of accelerators to fulfill diverse RALM requirements. Our Chameleon prototype implements retrieval accelerators on FPGAs and assigns LM inference to GPUs, with a CPU server orchestrating these accelerators over the network. Compared to CPU-based and CPU-GPU vector search systems, Chameleon achieves up to 23.72x speedup and 26.2x energy efficiency. Evaluated on various RALMs, Chameleon exhibits up to 2.16x reduction in latency and 3.18x speedup in throughput compared to the hybrid CPU-GPU architecture. These promising results pave the way for bringing accelerator heterogeneity and disaggregation into future RALM systems.
This paper considers the extension of data-enabled predictive control (DeePC) to nonlinear systems via general basis functions. Firstly, we formulate a basis functions DeePC behavioral predictor and we identify necessary and sufficient conditions for equivalence with a corresponding basis functions multi-step identified predictor. The derived conditions yield a dynamic regularization cost function that enables a well-posed (i.e., consistent) basis functions formulation of nonlinear DeePC. To optimize computational efficiency of basis functions DeePC we further develop two alternative formulations that use a simpler, sparse regularization cost function and ridge regression, respectively. Consistency implications for Koopman DeePC as well as several methods for constructing the basis functions representation are also indicated. The effectiveness of the developed consistent basis functions DeePC formulations is illustrated on a benchmark nonlinear pendulum state-space model, for both noise free and noisy data.
The Business Process Modeling Notation (BPMN) is a widely used standard notation for defining intra- and inter-organizational workflows. However, the informal description of the BPMN execution semantics leads to different interpretations of BPMN elements and difficulties in checking behavioral properties. In this article, we propose a formalization of the execution semantics of BPMN that, compared to existing approaches, covers more BPMN elements while also facilitating property checking. Our approach is based on a higher-order transformation from BPMN models to graph transformation systems. To show the capabilities of our approach, we implemented it as an open-source web-based tool. A demonstration of our tool is available at //youtu.be/MxXbNUl6IjE.
Screening mammography is the most widely used method for early breast cancer detection, significantly reducing mortality rates. The integration of information from multi-view mammograms enhances radiologists' confidence and diminishes false-positive rates since they can examine on dual-view of the same breast to cross-reference the existence and location of the lesion. Inspired by this, we present TransReg, a Computer-Aided Detection (CAD) system designed to exploit the relationship between craniocaudal (CC), and mediolateral oblique (MLO) views. The system includes cross-transformer to model the relationship between the region of interest (RoIs) extracted by siamese Faster RCNN network for mass detection problems. Our work is the first time cross-transformer has been integrated into an object detection framework to model the relation between ipsilateral views. Our experimental evaluation on DDSM and VinDr-Mammo datasets shows that our TransReg, equipped with SwinT as a feature extractor achieves state-of-the-art performance. Specifically, at the false positive rate per image at 0.5, TransReg using SwinT gets a recall at 83.3% for DDSM dataset and 79.7% for VinDr-Mammo dataset. Furthermore, we conduct a comprehensive analysis to demonstrate that cross-transformer can function as an auto-registration module, aligning the masses in dual-view and utilizing this information to inform final predictions. It is a replication diagnostic workflow of expert radiologists
Despite known differences between reading and listening in the brain, recent work has shown that text-based language models predict both text-evoked and speech-evoked brain activity to an impressive degree. This poses the question of what types of information language models truly predict in the brain. We investigate this question via a direct approach, in which we eliminate information related to specific low-level stimulus features (textual, speech, and visual) in the language model representations, and observe how this intervention affects the alignment with fMRI brain recordings acquired while participants read versus listened to the same naturalistic stories. We further contrast our findings with speech-based language models, which would be expected to predict speech-evoked brain activity better, provided they model language processing in the brain well. Using our direct approach, we find that both text-based and speech-based language models align well with early sensory regions due to shared low-level features. Text-based models continue to align well with later language regions even after removing these features, while, surprisingly, speech-based models lose most of their alignment. These findings suggest that speech-based models can be further improved to better reflect brain-like language processing.
When modeling a vector of risk variables, extreme scenarios are often of special interest. The peaks-over-thresholds method hinges on the notion that, asymptotically, the excesses over a vector of high thresholds follow a multivariate generalized Pareto distribution. However, existing literature has primarily concentrated on the setting when all risk variables are always large simultaneously. In reality, this assumption is often not met, especially in high dimensions. In response to this limitation, we study scenarios where distinct groups of risk variables may exhibit joint extremes while others do not. These discernible groups are derived from the angular measure inherent in the corresponding max-stable distribution, whence the term extreme direction. We explore such extreme directions within the framework of multivariate generalized Pareto distributions, with a focus on their probability density functions in relation to an appropriate dominating measure. Furthermore, we provide a stochastic construction that allows any prespecified set of risk groups to constitute the distribution's extreme directions. This construction takes the form of a smoothed max-linear model and accommodates the full spectrum of conceivable max-stable dependence structures. Additionally, we introduce a generic simulation algorithm tailored for multivariate generalized Pareto distributions, offering specific implementations for extensions of the logistic and H\"usler-Reiss families capable of carrying arbitrary extreme directions.
Accelerated life-tests (ALTs) are applied for inferring lifetime characteristics of highly reliable products. In particular, step-stress ALTs increase the stress level at which units under test are subject at certain pre-fixed times, thus accelerating product wear and inducing its failure. In some cases, due to cost or product nature constraints, continuous monitoring of devices is infeasible but the units are inspected for failures at particular inspection time points. In such setups, the ALT response is interval-censored. Furthermore, when a test unit fails, there are often more than one fatal cause for the failure, known as competing risks. In this paper, we assume that all competing risks are independent and follow an exponential distribution with scale parameter depending on the stress level. Under this setup, we present a family of robust estimators based on the density power divergence, including the classical maximum likelihood estimator as a particular case. We derive asymptotic and robustness properties of the MDPDE, showing its consistency for large samples. Based on these MDPDEs, estimates of the lifetime characteristics of the product as well as estimates of cause-specific lifetime characteristics have been developed. Direct, transformed and bootstrap confidence intervals for the mean lifetime to failure, reliability at a mission time, and distribution quantiles are proposed, and their performance is empirically compared through simulations. Besides, the performance of the MDPDE family has been examined through an extensive numerical study and the methods of inference discussed here are illustrated with a real-data example regarding electronic devices.
Numerous applications in the field of molecular communications (MC) such as healthcare systems are often event-driven. The conventional Shannon capacity may not be the appropriate metric for assessing performance in such cases. We propose the identification (ID) capacity as an alternative metric. Particularly, we consider randomized identification (RI) over the discrete-time Poisson channel (DTPC), which is typically used as a model for MC systems that utilize molecule-counting receivers. In the ID paradigm, the receiver's focus is not on decoding the message sent. However, he wants to determine whether a message of particular significance to him has been sent or not. In contrast to Shannon transmission codes, the size of ID codes for a Discrete Memoryless Channel (DMC) grows doubly exponentially fast with the blocklength, if randomized encoding is used. In this paper, we derive the capacity formula for RI over the DTPC subject to some peak and average power constraints. Furthermore, we analyze the case of state-dependent DTPC.
The goal of explainable Artificial Intelligence (XAI) is to generate human-interpretable explanations, but there are no computationally precise theories of how humans interpret AI generated explanations. The lack of theory means that validation of XAI must be done empirically, on a case-by-case basis, which prevents systematic theory-building in XAI. We propose a psychological theory of how humans draw conclusions from saliency maps, the most common form of XAI explanation, which for the first time allows for precise prediction of explainee inference conditioned on explanation. Our theory posits that absent explanation humans expect the AI to make similar decisions to themselves, and that they interpret an explanation by comparison to the explanations they themselves would give. Comparison is formalized via Shepard's universal law of generalization in a similarity space, a classic theory from cognitive science. A pre-registered user study on AI image classifications with saliency map explanations demonstrate that our theory quantitatively matches participants' predictions of the AI.
Graph representation learning for hypergraphs can be used to extract patterns among higher-order interactions that are critically important in many real world problems. Current approaches designed for hypergraphs, however, are unable to handle different types of hypergraphs and are typically not generic for various learning tasks. Indeed, models that can predict variable-sized heterogeneous hyperedges have not been available. Here we develop a new self-attention based graph neural network called Hyper-SAGNN applicable to homogeneous and heterogeneous hypergraphs with variable hyperedge sizes. We perform extensive evaluations on multiple datasets, including four benchmark network datasets and two single-cell Hi-C datasets in genomics. We demonstrate that Hyper-SAGNN significantly outperforms the state-of-the-art methods on traditional tasks while also achieving great performance on a new task called outsider identification. Hyper-SAGNN will be useful for graph representation learning to uncover complex higher-order interactions in different applications.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191