Search

We introduce a new spanning tree model called the random spanning tree in random environment (RSTRE), which interpolates between the uniform spanning tree and the minimum spanning tree as the inverse temperature (disorder strength) $\beta$ varies. On the complete graph with $n$ vertices and i.i.d.\ uniform disorder variables on the edges, we identify: (1) a low disorder regime with $\beta \leq C n/\log n$, where the diameter of the random spanning tree is typically of order $n^{1/2}$, the same as for the uniform spanning tree; (2) a high disorder regime with $\beta \geq n^{4/3} \log n$, where the diameter is typically of order $n^{1/3}$, the same as for the minimum spanning tree. We conjecture that for $\beta=n^{\alpha}$ with $\alpha \in (1, 4/3)$, the diameter is of order $n^{\gamma+o(1)}$ for some $\gamma=\gamma(\alpha)$ strictly between $1/2$ and $1/3$., Comment: 36 pages, 2 figures. Comments are welcome!

In high-resolution mass spectrometry, an electrospray ionization source is often paired with an ion-funnel to enhance ion transmission. Although it is established that ions experience collision-induced dissociation as they pass through this device, the impact of gas-flow dynamics on ion fragmentation remains unexplored. The present work demonstrates that the gas-flow dynamics from the capillary interface of an electrospray ionization source into an ion-funnel significantly reduces ion fragmentation. This reduction stems from the substantial decrease in the rate of increase in the internal energy of the ions resulting from the collisions with a supersonically expanding gas. The results of this study have significant consequences for systems that employ electrospray mass spectrometry and ion-mobility spectrometry.

When dealing with multimedia data, source attribution is a key challenge from a forensic perspective. This task aims to determine how a given content was captured, providing valuable insights for various applications, including legal proceedings and integrity investigations. The source attribution problem has been addressed in different domains, from identifying the camera model used to capture specific photographs to detecting the synthetic speech generator or microphone model used to create or record given audio tracks. Recent advancements in this area rely heavily on machine learning and data-driven techniques, which often outperform traditional signal processing-based methods. However, a drawback of these systems is their need for large volumes of training data, which must reflect the latest technological trends to produce accurate and reliable predictions. This presents a significant challenge, as the rapid pace of technological progress makes it difficult to maintain datasets that are up-to-date with real-world conditions. For instance, in the task of smartphone model identification from audio recordings, the available datasets are often outdated or acquired inconsistently, making it difficult to develop solutions that are valid beyond a research environment. In this paper we present POLIPHONE, a dataset for smartphone model identification from audio recordings. It includes data from 20 recent smartphones recorded in a controlled environment to ensure reproducibility and scalability for future research. The released tracks contain audio data from various domains (i.e., speech, music, environmental sounds), making the corpus versatile and applicable to a wide range of use cases. We also present numerous experiments to benchmark the proposed dataset using a state-of-the-art classifier for smartphone model identification from audio recordings., Comment: Submitted to IEEE Access

Skid-steered wheel mobile robots (SSWMRs) operate in a variety of outdoor environments exhibiting motion behaviors dominated by the effects of complex wheel-ground interactions. Characterizing these interactions is crucial both from the immediate robot autonomy perspective (for motion prediction and control) as well as a long-term predictive maintenance and diagnostics perspective. An ideal solution entails capturing precise state measurements for decisions and controls, which is considerably difficult, especially in increasingly unstructured outdoor regimes of operations for these robots. In this milieu, a framework to identify pre-determined discrete modes of operation can considerably simplify the motion model identification process. To this end, we propose an interactive multiple model (IMM) based filtering framework to probabilistically identify predefined robot operation modes that could arise due to traversal in different terrains or loss of wheel traction.

In speech deepfake detection, one of the critical aspects is developing detectors able to generalize on unseen data and distinguish fake signals across different datasets. Common approaches to this challenge involve incorporating diverse data into the training process or fine-tuning models on unseen datasets. However, these solutions can be computationally demanding and may lead to the loss of knowledge acquired from previously learned data. Continual learning techniques offer a potential solution to this problem, allowing the models to learn from unseen data without losing what they have already learned. Still, the optimal way to apply these algorithms for speech deepfake detection remains unclear, and we do not know which is the best way to apply these algorithms to the developed models. In this paper we address this aspect and investigate whether, when retraining a speech deepfake detector, it is more effective to apply continual learning across the entire model or to update only some of its layers while freezing others. Our findings, validated across multiple models, indicate that the most effective approach among the analyzed ones is to update only the weights of the initial layers, which are responsible for processing the input features of the detector., Comment: Submitted to ICASSP 2025

Speech deepfakes pose a significant threat to personal security and content authenticity. Several detectors have been proposed in the literature, and one of the primary challenges these systems have to face is the generalization over unseen data to identify fake signals across a wide range of datasets. In this paper, we introduce a novel approach for enhancing speech deepfake detection performance using a Mixture of Experts architecture. The Mixture of Experts framework is well-suited for the speech deepfake detection task due to its ability to specialize in different input types and handle data variability efficiently. This approach offers superior generalization and adaptability to unseen data compared to traditional single models or ensemble methods. Additionally, its modular structure supports scalable updates, making it more flexible in managing the evolving complexity of deepfake techniques while maintaining high detection accuracy. We propose an efficient, lightweight gating mechanism to dynamically assign expert weights for each input, optimizing detection performance. Experimental results across multiple datasets demonstrate the effectiveness and potential of our proposed approach., Comment: Submitted to ICASSP 2025

Stabilizing vertical dynamics for on-road and off-road vehicles is an important research area that has been looked at mostly from the point of view of ride comfort. The advent of autonomous vehicles now shifts the focus more towards developing stabilizing techniques from the point of view of onboard proprioceptive and exteroceptive sensors whose real-time measurements influence the performance of an autonomous vehicle. The current solutions to this problem of managing the vertical oscillations usually limit themselves to the realm of active suspension systems without much consideration to modulating the vehicle velocity, which plays an important role by the virtue of the fact that vertical and longitudinal dynamics of a ground vehicle are coupled. The task of stabilizing vertical oscillations for military ground vehicles becomes even more challenging due lack of structured environments, like city roads or highways, in off-road scenarios. Moreover, changes in structural parameters of the vehicle, such as mass (due to changes in vehicle loading), suspension stiffness and damping values can have significant effect on the controller's performance. This demands the need for developing deep learning based control policies, that can take into account an extremely large number of input features and approximate a near optimal control action. In this work, these problems are addressed by training a deep reinforcement learning agent to minimize the vertical acceleration of a scaled vehicle travelling over bumps by controlling its velocity.

Speech deepfake detection has recently gained significant attention within the multimedia forensics community. Related issues have also been explored, such as the identification of partially fake signals, i.e., tracks that include both real and fake speech segments. However, generating high-quality spliced audio is not as straightforward as it may appear. Spliced signals are typically created through basic signal concatenation. This process could introduce noticeable artifacts that can make the generated data easier to detect. We analyze spliced audio tracks resulting from signal concatenation, investigate their artifacts and assess whether such artifacts introduce any bias in existing datasets. Our findings reveal that by analyzing splicing artifacts, we can achieve a detection EER of 6.16% and 7.36% on PartialSpoof and HAD datasets, respectively, without needing to train any detector. These results underscore the complexities of generating reliable spliced audio data and lead to discussions that can help improve future research in this area., Comment: Accepted at ASVspoof 5 Workshop (Interspeech2024 Satellite)

AI assistants are being increasingly used by students enrolled in higher education institutions. While these tools provide opportunities for improved teaching and education, they also pose significant challenges for assessment and learning outcomes. We conceptualize these challenges through the lens of vulnerability, the potential for university assessments and learning outcomes to be impacted by student use of generative AI. We investigate the potential scale of this vulnerability by measuring the degree to which AI assistants can complete assessment questions in standard university-level STEM courses. Specifically, we compile a novel dataset of textual assessment questions from 50 courses at EPFL and evaluate whether two AI assistants, GPT-3.5 and GPT-4 can adequately answer these questions. We use eight prompting strategies to produce responses and find that GPT-4 answers an average of 65.8% of questions correctly, and can even produce the correct answer across at least one prompting strategy for 85.1% of questions. When grouping courses in our dataset by degree program, these systems already pass non-project assessments of large numbers of core courses in various degree programs, posing risks to higher education accreditation that will be amplified as these models improve. Our results call for revising program-level assessment design in higher education in light of advances in generative AI., Comment: 20 pages, 8 figures

AI-generated synthetic media, also called Deepfakes, have significantly influenced so many domains, from entertainment to cybersecurity. Generative Adversarial Networks (GANs) and Diffusion Models (DMs) are the main frameworks used to create Deepfakes, producing highly realistic yet fabricated content. While these technologies open up new creative possibilities, they also bring substantial ethical and security risks due to their potential misuse. The rise of such advanced media has led to the development of a cognitive bias known as Impostor Bias, where individuals doubt the authenticity of multimedia due to the awareness of AI's capabilities. As a result, Deepfake detection has become a vital area of research, focusing on identifying subtle inconsistencies and artifacts with machine learning techniques, especially Convolutional Neural Networks (CNNs). Research in forensic Deepfake technology encompasses five main areas: detection, attribution and recognition, passive authentication, detection in realistic scenarios, and active authentication. This paper reviews the primary algorithms that address these challenges, examining their advantages, limitations, and future prospects.

We present a unified approach to obtain scaling limits of neural networks using the genus expansion technique from random matrix theory. This approach begins with a novel expansion of neural networks which is reminiscent of Butcher series for ODEs, and is obtained through a generalisation of Fa\`a di Bruno's formula to an arbitrary number of compositions. In this expansion, the role of monomials is played by random multilinear maps indexed by directed graphs whose edges correspond to random matrices, which we call operator graphs. This expansion linearises the effect of the activation functions, allowing for the direct application of Wick's principle to compute the expectation of each of its terms. We then determine the leading contribution to each term by embedding the corresponding graphs onto surfaces, and computing their Euler characteristic. Furthermore, by developing a correspondence between analytic and graphical operations, we obtain similar graph expansions for the neural tangent kernel as well as the input-output Jacobian of the original neural network, and derive their infinite-width limits with relative ease. Notably, we find explicit formulae for the moments of the limiting singular value distribution of the Jacobian. We then show that all of these results hold for networks with more general weights, such as general matrices with i.i.d. entries satisfying moment assumptions, complex matrices and sparse matrices., Comment: v4: minor changes to presentation

We show the convergence of the solutions to the massive nonlinear Klein-Gordon equation toward solutions to a relativistic Euler with potential type system in the semi-classical limit. In particular, the momentum and the density of Klein-Gordon converge to the the momentum and the density of the relativistic Euler system in Lebesgue norms. The relativistic Euler with potential is equivalent to the usual relativistic Euler with pressure up to a rescaling. The proof relies on the modulated energy method adapted to the wave equation and the relativistic setting.

We study a 1-parameter family (A{\lambda}, {\Phi}{\lambda}){\lambda} of multi-phase high frequency solutions to Klein-Gordon-Maxwell equations in Lorenz gauge in the (3+1)-dimensional Minkowski spacetime. This family is based on an initial ansatz. We prove that for {\lambda} small enough the family of solutions exists on an interval uniform in {\lambda} only function of the initial ansatz. These solutions are close to an approximate solution constructed by geometric optics. The initial ansatz needs to be regular enough, to satisfy a polarization condition and to satisfy the constraints for Maxwell null-transport in Lorenz gauge, but there is no need for smallness of any kind. The phases need to interact in a coherent way. We also observe that the limit (A0, {\Phi}0) is not solution to Klein-Gordon-Maxwell equations but to a Klein-Gordon-Maxwell null-transport type system.

This work is concerned with devising a robust Parkinson's (PD) disease detector from speech in real-world operating conditions using (i) foundational models, and (ii) speech enhancement (SE) methods. To this end, we first fine-tune several foundational-based models on the standard PC-GITA (s-PC-GITA) clean data. Our results demonstrate superior performance to previously proposed models. Second, we assess the generalization capability of the PD models on the extended PC-GITA (e-PC-GITA) recordings, collected in real-world operative conditions, and observe a severe drop in performance moving from ideal to real-world conditions. Third, we align training and testing conditions applaying off-the-shelf SE techniques on e-PC-GITA, and a significant boost in performance is observed only for the foundational-based models. Finally, combining the two best foundational-based models trained on s-PC-GITA, namely WavLM Base and Hubert Base, yielded top performance on the enhanced e-PC-GITA., Comment: Accepted at INTERSPEECH 2024

In 2021, Adam Zsolt Wagner proposed an approach to disprove conjectures in graph theory using Reinforcement Learning (RL). Wagner's idea can be framed as follows: consider a conjecture, such as a certain quantity f(G) < 0 for every graph G; one can then play a single-player graph-building game, where at each turn the player decides whether to add an edge or not. The game ends when all edges have been considered, resulting in a certain graph G_T, and f(G_T) is the final score of the game; RL is then used to maximize this score. This brilliant idea is as simple as innovative, and it lends itself to systematic generalization. Several different single-player graph-building games can be employed, along with various RL algorithms. Moreover, RL maximizes the cumulative reward, allowing for step-by-step rewards instead of a single final score, provided the final cumulative reward represents the quantity of interest f(G_T). In this paper, we discuss these and various other choices that can be significant in Wagner's framework. As a contribution to this systematization, we present four distinct single-player graph-building games. Each game employs both a step-by-step reward system and a single final score. We also propose a principled approach to select the most suitable neural network architecture for any given conjecture, and introduce a new dataset of graphs labeled with their Laplacian spectra. Furthermore, we provide a counterexample for a conjecture regarding the sum of the matching number and the spectral radius, which is simpler than the example provided in Wagner's original paper. The games have been implemented as environments in the Gymnasium framework, and along with the dataset, are available as open-source supplementary materials., Comment: Accepted at the 27th International Conference on Discovery Science http://ds2024.isti.cnr.it/

Score-based diffusion models have recently emerged as state-of-the-art generative models for a variety of data modalities. Nonetheless, it remains unclear how to adapt these models to generate long multivariate time series. Viewing a time series as the discretization of an underlying continuous process, we introduce SigDiffusion, a novel diffusion model operating on log-signature embeddings of the data. The forward and backward processes gradually perturb and denoise log-signatures preserving their algebraic structure. To recover a signal from its log-signature, we provide new closed-form inversion formulae expressing the coefficients obtained by expanding the signal in a given basis (e.g. Fourier or orthogonal polynomials) as explicit polynomial functions of the log-signature. Finally, we show that combining SigDiffusion with these inversion formulae results in highly realistic time series generation, competitive with the current state-of-the-art on various datasets of synthetic and real-world examples.

We introduce a mathematically rigorous framework based on rough path theory to model stochastic spiking neural networks (SSNNs) as stochastic differential equations with event discontinuities (Event SDEs) and driven by c\`adl\`ag rough paths. Our formalism is general enough to allow for potential jumps to be present both in the solution trajectories as well as in the driving noise. We then identify a set of sufficient conditions ensuring the existence of pathwise gradients of solution trajectories and event times with respect to the network's parameters and show how these gradients satisfy a recursive relation. Furthermore, we introduce a general-purpose loss function defined by means of a new class of signature kernels indexed on c\`adl\`ag rough paths and use it to train SSNNs as generative models. We provide an end-to-end autodifferentiable solver for Event SDEs and make its implementation available as part of the $\texttt{diffrax}$ library. Our framework is, to our knowledge, the first enabling gradient-based training of SSNNs with noise affecting both the spike timing and the network's dynamics.

It is well-known that randomly initialized, push-forward, fully-connected neural networks weakly converge to isotropic Gaussian processes, in the limit where the width of all layers goes to infinity. In this paper, we propose to use the angular power spectrum of the limiting field to characterize the complexity of the network architecture. In particular, we define sequences of random variables associated with the angular power spectrum, and provide a full characterization of the network complexity in terms of the asymptotic distribution of these sequences as the depth diverges. On this basis, we classify neural networks as low-disorder, sparse, or high-disorder; we show how this classification highlights a number of distinct features for standard activation functions, and in particular, sparsity properties of ReLU networks. Our theoretical results are also validated by numerical simulations.

2D texture maps and 3D voxel arrays are widely used to add rich detail to the surfaces and volumes of rendered scenes, and filtered texture lookups are integral to producing high-quality imagery. We show that applying the texture filter after evaluating shading generally gives more accurate imagery than filtering textures before BSDF evaluation, as is current practice. These benefits are not merely theoretical, but are apparent in common cases. We demonstrate that practical and efficient filtering after shading is possible through the use of stochastic sampling of texture filters. Stochastic texture filtering offers additional benefits, including efficient implementation of high-quality texture filters and efficient filtering of textures stored in compressed and sparse data structures, including neural representations. We demonstrate applications in both real-time and offline rendering and show that the additional error from stochastic filtering is minimal. We find that this error is handled well by either spatiotemporal denoising or moderate pixel sampling rates., Comment: arXiv admin note: substantial text overlap with arXiv:2305.05810

This paper is concerned with automatic continuous speech recognition using trainable systems. The aim of this work is to build acoustic models for spoken Swedish. This is done employing hidden Markov models and using the SpeechDat database to train their parameters. Acoustic modeling has been worked out at a phonetic level, allowing general speech recognition applications, even though a simplified task (digits and natural number recognition) has been considered for model evaluation. Different kinds of phone models have been tested, including context independent models and two variations of context dependent models. Furthermore many experiments have been done with bigram language models to tune some of the system parameters. System performance over various speaker subsets with different sex, age and dialect has also been examined. Results are compared to previous similar studies showing a remarkable improvement., Comment: 16 pages, 7 figures

Methods that can generate synthetic speech which is perceptually indistinguishable from speech recorded by a human speaker, are easily available. Several incidents report misuse of synthetic speech generated from these methods to commit fraud. To counter such misuse, many methods have been proposed to detect synthetic speech. Some of these detectors are more interpretable, can generalize to detect synthetic speech in the wild and are robust to noise. However, limited work has been done on understanding bias in these detectors. In this work, we examine bias in existing synthetic speech detectors to determine if they will unfairly target a particular gender, age and accent group. We also inspect whether these detectors will have a higher misclassification rate for bona fide speech from speech-impaired speakers w.r.t fluent speakers. Extensive experiments on 6 existing synthetic speech detectors using more than 0.9 million speech signals demonstrate that most detectors are gender, age and accent biased, and future work is needed to ensure fairness. To support future research, we release our evaluation dataset, models used in our study and source code at https://gitlab.com/viper-purdue/fairssd., Comment: Accepted at CVPR 2024 (WMF)

These notes expound the recent use of the signature transform and rough path theory in data science and machine learning. We develop the core theory of the signature from first principles and then survey some recent popular applications of this approach, including signature-based kernel methods and neural rough differential equations. The notes are based on a course given by the two authors at Imperial College London.

The development and popularization of large language models (LLMs) have raised concerns that they will be used to create tailor-made, convincing arguments to push false or misleading narratives online. Early work has found that language models can generate content perceived as at least on par and often more persuasive than human-written messages. However, there is still limited knowledge about LLMs' persuasive capabilities in direct conversations with human counterparts and how personalization can improve their performance. In this pre-registered study, we analyze the effect of AI-driven persuasion in a controlled, harmless setting. We create a web-based platform where participants engage in short, multiple-round debates with a live opponent. Each participant is randomly assigned to one of four treatment conditions, corresponding to a two-by-two factorial design: (1) Games are either played between two humans or between a human and an LLM; (2) Personalization might or might not be enabled, granting one of the two players access to basic sociodemographic information about their opponent. We found that participants who debated GPT-4 with access to their personal information had 81.7% (p < 0.01; N=820 unique participants) higher odds of increased agreement with their opponents compared to participants who debated humans. Without personalization, GPT-4 still outperforms humans, but the effect is lower and statistically non-significant (p=0.31). Overall, our results suggest that concerns around personalization are meaningful and have important implications for the governance of social media and the design of new online environments., Comment: 33 pages, 10 figures, 7 tables

We develop a provably convergent kernel-based solver for path-dependent PDEs (PPDEs). Our numerical scheme leverages signature kernels, a recently introduced class of kernels on path-space. Specifically, we solve an optimal recovery problem by approximating the solution of a PPDE with an element of minimal norm in the signature reproducing kernel Hilbert space (RKHS) constrained to satisfy the PPDE at a finite collection of collocation paths. In the linear case, we show that the optimisation has a unique closed-form solution expressed in terms of signature kernel evaluations at the collocation paths. We prove consistency of the proposed scheme, guaranteeing convergence to the PPDE solution as the number of collocation points increases. Finally, several numerical examples are presented, in particular in the context of option pricing under rough volatility. Our numerical scheme constitutes a valid alternative to the ubiquitous Monte Carlo methods., Comment: 35 pages, 1 figure

Recently uncovered archives at the University of Franche-Comt\'e in Besan\c{c}on (France) reveal a rich history of research and teaching in physics since the Faculty of Science was first established in 1845. Here, we describe a selection of notable activities conducted by the named Chairs of Physics during the period 1845-1970. We uncover a long tradition of major contributions to physics education and research, including the production of highly regarded physics textbooks that were widely used in Europe, as well as pioneering contributions to electron diffraction and microscopy, Fourier optics, and holography. These discoveries yield valuable insights into the historical development of physics research in France, and show how even a small provincial university was able to stay up-to-date with international developments across several areas of physics.

Structured state-space models (SSMs) such as S4, stemming from the seminal work of Gu et al., are gaining popularity as effective approaches for modeling sequential data. Deep SSMs demonstrate outstanding performance across a diverse set of domains, at a reduced training and inference cost compared to attention-based transformers. Recent developments show that if the linear recurrence powering SSMs allows for multiplicative interactions between inputs and hidden states (e.g. GateLoop, Mamba, GLA), then the resulting architecture can surpass in both in accuracy and efficiency attention-powered foundation models trained on text, at scales of billion parameters. In this paper, we give theoretical grounding to this recent finding using tools from Rough Path Theory: we show that when random linear recurrences are equipped with simple input-controlled transitions (selectivity mechanism), then the hidden state is provably a low-dimensional projection of a powerful mathematical object called the signature of the input -- capturing non-linear interactions between tokens at distinct timescales. Our theory not only motivates the success of modern selective state-space models such as Mamba but also provides a solid framework to understand the expressive power of future SSM variants., Comment: NeurIPS Version w/ minor edits

Inferring the causal structure underlying stochastic dynamical systems from observational data holds great promise in domains ranging from science and health to finance. Such processes can often be accurately modeled via stochastic differential equations (SDEs), which naturally imply causal relationships via "which variables enter the differential of which other variables". In this paper, we develop conditional independence (CI) constraints on coordinate processes over selected intervals that are Markov with respect to the acyclic dependence graph (allowing self-loops) induced by a general SDE model. We then provide a sound and complete causal discovery algorithm, capable of handling both fully and partially observed data, and uniquely recovering the underlying or induced ancestral graph by exploiting time directionality assuming a CI oracle. Finally, to make our algorithm practically usable, we also propose a flexible, consistent signature kernel-based CI test to infer these constraints from data. We extensively benchmark the CI test in isolation and as part of our causal discovery algorithms, outperforming existing approaches in SDE models and beyond.

Recent advancements in synthetic speech generation have led to the creation of forged audio data that are almost indistinguishable from real speech. This phenomenon poses a new challenge for the multimedia forensics community, as the misuse of synthetic media can potentially cause adverse consequences. Several methods have been proposed in the literature to mitigate potential risks and detect synthetic speech, mainly focusing on the analysis of the speech itself. However, recent studies have revealed that the most crucial frequency bands for detection lie in the highest ranges (above 6000 Hz), which do not include any speech content. In this work, we extensively explore this aspect and investigate whether synthetic speech detection can be performed by focusing only on the background component of the signal while disregarding its verbal content. Our findings indicate that the speech component is not the predominant factor in performing synthetic speech detection. These insights provide valuable guidance for the development of new synthetic speech detectors and their interpretability, together with some considerations on the existing work in the audio forensics field.

Quantitative data is frequently represented using color, yet designing effective color mappings is a challenging task, requiring one to balance perceptual standards with personal color preference. Current design tools either overwhelm novices with complexity or offer limited customization options. We present ColorMaker, a mixed-initiative approach for creating colormaps. ColorMaker combines fluid user interaction with real-time optimization to generate smooth, continuous color ramps. Users specify their loose color preferences while leaving the algorithm to generate precise color sequences, meeting both designer needs and established guidelines. ColorMaker can create new colormaps, including designs accessible for people with color-vision deficiencies, starting from scratch or with only partial input, thus supporting ideation and iterative refinement. We show that our approach can generate designs with similar or superior perceptual characteristics to standard colormaps. A user study demonstrates how designers of varying skill levels can use this tool to create custom, high-quality colormaps. ColorMaker is available at https://colormaker.org, Comment: To appear at the ACM CHI '24 Conference on Human Factors in Computing Systems

In many scientific disciplines, the features of interest cannot be observed directly, so must instead be inferred from observed behaviour. Latent variable analyses are increasingly employed to systematise these inferences, and Principal Components Analysis (PCA) is perhaps the simplest and most popular of these methods. Here, we examine how the assumptions that we are prepared to entertain, about the latent variable system, mediate the likelihood that PCA-derived components will capture the true sources of variance underlying data. As expected, we find that this likelihood is excellent in the best case, and robust to empirically reasonable levels of measurement noise, but best-case performance is also: (a) not robust to violations of the method's more prominent assumptions, of linearity and orthogonality; and also (b) requires that other subtler assumptions be made, such as that the latent variables should have varying importance, and that weights relating latent variables to observed data have zero mean. Neither variance explained, nor replication in independent samples, could reliably predict which (if any) PCA-derived components will capture true sources of variance in data. We conclude by describing a procedure to fit these inferences more directly to empirical data, and use it to find that components derived via PCA from two different empirical neuropsychological datasets, are less likely to have meaningful referents in the brain than we hoped., Comment: 26 pages, 3 figures, 3 tables

This paper describes the use of connectionist techniques in phonetic speech recognition with strong latency constraints. The constraints are imposed by the task of deriving the lip movements of a synthetic face in real time from the speech signal, by feeding the phonetic string into an articulatory synthesiser. Particular attention has been paid to analysing the interaction between the time evolution model learnt by the multi-layer perceptrons and the transition model imposed by the Viterbi decoder, in different latency conditions. Two experiments were conducted in which the time dependencies in the language model (LM) were controlled by a parameter. The results show a strong interaction between the three factors involved, namely the neural network topology, the length of time dependencies in the LM and the decoder latency.

This article investigates the possibility to use the class entropy of the output of a connectionist phoneme recogniser to predict time boundaries between phonetic classes. The rationale is that the value of the entropy should increase in proximity of a transition between two segments that are well modelled (known) by the recognition network since it is a measure of uncertainty. The advantage of this measure is its simplicity as the posterior probabilities of each class are available in connectionist phoneme recognition. The entropy and a number of measures based on differentiation of the entropy are used in isolation and in combination. The decision methods for predicting the boundaries range from simple thresholds to neural network based procedure. The different methods are compared with respect to their precision, measured in terms of the ratio between the number C of predicted boundaries within 10 or 20 msec of the reference and the total number of predicted boundaries, and recall, measured as the ratio between C and the total number of reference boundaries.

The Circle of Willis (CoW) is an important network of arteries connecting major circulations of the brain. Its vascular architecture is believed to affect the risk, severity, and clinical outcome of serious neuro-vascular diseases. However, characterizing the highly variable CoW anatomy is still a manual and time-consuming expert task. The CoW is usually imaged by two angiographic imaging modalities, magnetic resonance angiography (MRA) and computed tomography angiography (CTA), but there exist limited public datasets with annotations on CoW anatomy, especially for CTA. Therefore we organized the TopCoW Challenge in 2023 with the release of an annotated CoW dataset. The TopCoW dataset was the first public dataset with voxel-level annotations for thirteen possible CoW vessel components, enabled by virtual-reality (VR) technology. It was also the first large dataset with paired MRA and CTA from the same patients. TopCoW challenge formalized the CoW characterization problem as a multiclass anatomical segmentation task with an emphasis on topological metrics. We invited submissions worldwide for the CoW segmentation task, which attracted over 140 registered participants from four continents. The top performing teams managed to segment many CoW components to Dice scores around 90%, but with lower scores for communicating arteries and rare variants. There were also topological mistakes for predictions with high Dice scores. Additional topological analysis revealed further areas for improvement in detecting certain CoW components and matching CoW variant topology accurately. TopCoW represented a first attempt at benchmarking the CoW anatomical segmentation task for MRA and CTA, both morphologically and topologically., Comment: 24 pages, 11 figures, 9 tables. Summary Paper for the MICCAI TopCoW 2023 Challenge