EnK: Encoding time-information in convolution

Recent development in deep learning techniques has attracted attention in decoding and classification in EEG signals. Despite several efforts utilizing different features of EEG signals, a significant research challenge is to use time-dependent features in combination with local and global features. There have been several efforts to remodel the deep learning convolution neural networks (CNNs) to capture time-dependency information by incorporating hand-crafted features, slicing the input data in a smaller time-windows, and recurrent convolution. However, these approaches partially solve the problem, but simultaneously hinder the CNN's capability to learn from unknown information that might be present in the data. To solve this, we have proposed a novel time encoding kernel (EnK) approach, which introduces the increasing time information during convolution operation in CNN. The encoded information by EnK lets CNN learn time-dependent features in-addition to local and global features. We performed extensive experiments on several EEG datasets: cognitive conflict (CC), physical-human robot collaboration (pHRC), P300 visual-evoked potentials, movement-related cortical potentials (MRCP). EnK outperforms the state-of-art by 12\% (F1 score). Moreover, the EnK approach required only one additional parameter to learn and can be applied to a virtually any CNN architectures with minimal efforts. These results support our methodology and show high potential to improve CNN performance in the context of time-series data in general.

Linear time DBSCAN for sorted 1D data and laser range scan segmentation

This paper introduces new algorithm for line extraction from laser range data including methodology for efficient computation. The task is cast to series of one dimensional problems in various spaces. A fast and simple specialization of DBSCAN algorithm is proposed to solve one dimensional subproblems. Experiments suggest that the method is suitable for real-time applications, handles noise well and may be useful in practice.

Probabilistic Embeddings with Laplacian Graph Priors

We introduce probabilistic embeddings using Laplacian priors (PELP). The proposed model enables incorporating graph side-information into static word embeddings. We theoretically show that the model unifies several previously proposed embedding methods under one umbrella. PELP generalises graph-enhanced, group, dynamic, and cross-lingual static word embeddings. PELP also enables any combination of these previous models in a straightforward fashion. Furthermore, we empirically show that our model matches the performance of previous models as special cases. In addition, we demonstrate its flexibility by applying it to the comparison of political sociolects over time. Finally, we provide code as a TensorFlow implementation enabling flexible estimation in different settings.

Dynamic Infection Spread Model Based Group Testing

We study a dynamic infection spread model, inspired by the discrete time SIR model, where infections are spread via non-isolated infected individuals. While infection keeps spreading over time, a limited capacity testing is performed at each time instance as well. In contrast to the classical, static, group testing problem, the objective in our setup is not to find the minimum number of required tests to identify the infection status of every individual in the population, but to control the infection spread by detecting and isolating the infections over time by using the given, limited number of tests. In order to analyze the performance of the proposed algorithms, we focus on the mean-sense analysis of the number of individuals that remain non-infected throughout the process of controlling the infection. We propose two dynamic algorithms that both use given limited number of tests to identify and isolate the infections over time, while the infection spreads. While the first algorithm is a dynamic randomized individual testing algorithm, in the second algorithm we employ the group testing approach similar to the original work of Dorfman. By considering weak versions of our algorithms, we obtain lower bounds for the performance of our algorithms. Finally, we implement our algorithms and run simulations to gather numerical results and compare our algorithms and theoretical approximation results under different sets of system parameters.

EmotionNAS: Two-stream Architecture Search for Speech Emotion Recognition

Speech emotion recognition (SER) is a crucial research topic in human-computer interactions. Existing works are mainly based on manually designed models. Despite their great success, these methods heavily rely on historical experience, which are time-consuming but cannot exhaust all possible structures. To address this problem, we propose a neural architecture search (NAS) based framework for SER, called "EmotionNAS". We take spectrogram and wav2vec features as the inputs, followed with NAS to optimize the network structure for these features separately. We further incorporate complementary information in these features through decision-level fusion. Experimental results on IEMOCAP demonstrate that our method succeeds over existing state-of-the-art strategies on SER.

Theoretical Understanding of the Information Flow on Continual Learning Performance

Continual learning (CL) is a setting in which an agent has to learn from an incoming stream of data sequentially. CL performance evaluates the model's ability to continually learn and solve new problems with incremental available information over time while retaining previous knowledge. Despite the numerous previous solutions to bypass the catastrophic forgetting (CF) of previously seen tasks during the learning process, most of them still suffer significant forgetting, expensive memory cost, or lack of theoretical understanding of neural networks' conduct while learning new tasks. While the issue that CL performance degrades under different training regimes has been extensively studied empirically, insufficient attention has been paid from a theoretical angle. In this paper, we establish a probabilistic framework to analyze information flow through layers in networks for task sequences and its impact on learning performance. Our objective is to optimize the information preservation between layers while learning new tasks to manage task-specific knowledge passing throughout the layers while maintaining model performance on previous tasks. In particular, we study CL performance's relationship with information flow in the network to answer the question "How can knowledge of information flow between layers be used to alleviate CF?". Our analysis provides novel insights of information adaptation within the layers during the incremental task learning process. Through our experiments, we provide empirical evidence and practically highlight the performance improvement across multiple tasks.

A Learnable Variational Model for Joint Multimodal MRI Reconstruction and Synthesis

Generating multi-contrasts/modal MRI of the same anatomy enriches diagnostic information but is limited in practice due to excessive data acquisition time. In this paper, we propose a novel deep-learning model for joint reconstruction and synthesis of multi-modal MRI using incomplete k-space data of several source modalities as inputs. The output of our model includes reconstructed images of the source modalities and high-quality image synthesized in the target modality. Our proposed model is formulated as a variational problem that leverages several learnable modality-specific feature extractors and a multimodal synthesis module. We propose a learnable optimization algorithm to solve this model, which induces a multi-phase network whose parameters can be trained using multi-modal MRI data. Moreover, a bilevel-optimization framework is employed for robust parameter training. We demonstrate the effectiveness of our approach using extensive numerical experiments.

Improving tracking with a tracklet associator

Multiple object tracking (MOT) is a task in computer vision that aims to detect the position of various objects in videos and to associate them to a unique identity. We propose an approach based on Constraint Programming (CP) whose goal is to be grafted to any existing tracker in order to improve its object association results. We developed a modular algorithm divided into three independent phases. The first phase consists in recovering the tracklets provided by a base tracker and to cut them at the places where uncertain associations are spotted, for example, when tracklets overlap, which may cause identity switches. In the second phase, we associate the previously constructed tracklets using a Belief Propagation Constraint Programming algorithm, where we propose various constraints that assign scores to each of the tracklets based on multiple characteristics, such as their dynamics or the distance between them in time and space. Finally, the third phase is a rudimentary interpolation model to fill in the remaining holes in the trajectories we built. Experiments show that our model leads to improvements in the results for all three of the state-of-the-art trackers on which we tested it (3 to 4 points gained on HOTA and IDF1).

MIMO Channel Estimation using Score-Based Generative Models

Channel estimation is a critical task in multiple-input multiple-output digital communications that has effects on end-to-end system performance. In this work, we introduce a novel approach for channel estimation using deep score-based generative models. These models are trained to estimate the gradient of the log-prior distribution, and can be used to iteratively refine estimates, given observed measurements of a signal. We introduce a framework for training score-based generative models for wireless channels, as well as performing channel estimation using posterior sampling at test time. We derive theoretical robustness guarantees of channel estimation with posterior sampling in single-input single-output scenarios, and show that the observations regarding estimation performance are verified experimentally in MIMO channels. Our results in simulated clustered delay line channels show competitive in-distribution performance without error floors in the high signal-to-noise ratio regime, and robust out-of-distribution performance, outperforming competing deep learning methods by up to 5 dB in end-to-end communication performance, while the complexity analysis reveals how model architecture can efficiently trade performance for estimation latency.

Forecasting Market Changes using Variational Inference

Though various approaches have been considered, forecasting near-term market changes of equities and similar market data remains quite difficult. In this paper we introduce an approach to forecast near-term market changes for equity indices as well as portfolios using variational inference (VI). VI is a machine learning approach which uses optimization techniques to estimate complex probability densities. In the proposed approach, clusters of explanatory variables are identified and market changes are forecast based on cluster-specific linear regression. Apart from the expected value of changes, the proposed approach can also be used to obtain the distribution of possible outcomes, which can be used to estimate confidence levels of forecasts and risk measures such as VaR (Value at Risk) for the portfolio. Another advantage of the proposed approach is the clear model interpretation, as clusters of explanatory variables (or market regimes) are identified for which the future changes follow similar relationships. Knowledge about such clusters can provide useful insights about portfolio performance and identify the relative importance of variables in different market regimes. Illustrative examples of equity and bond indices are considered to demonstrate forecasts of the proposed approach during Covid-related volatility in early 2020 and subsequent benign market conditions. For the portfolios considered, it is shown that the proposed approach provides useful forecasts in both normal and volatile markets even with only a few explanatory variables. Additionally the predicted estimate and distribution adapt quickly to changing market conditions and thus may also be useful in obtaining better real-time estimates of risk measures such as VaR compared to traditional approaches.