Boosting Weakly Supervised Object Localization and Segmentation With Domain Adaption.

Weakly supervised object localization (WSOL), adopting only image-level annotations to learn the pixel-level localization model, can release human resources in the annotation process. Most one-stage WSOL methods learn the localization model with multi-instance learning, making them only activate discriminative object parts rather than the whole object. In our work, we attribute this problem to the domain shift between the training and test process of WSOL and provide a novel perspective that views WSOL as a domain adaption (DA) task.

The association of SOD and HsCRP with the efficacy of sulforaphane in schizophrenia patients with residual negative symptoms.

Objectives: Emerging evidence indicates a connection between oxidative stress, immune-inflammatory processes, and the negative symptoms of schizophrenia. In addition to possessing potent antioxidant and anti-inflammatory properties, sulforaphane (SFN) has shown promise in enhancing cognitive function among individuals with schizophrenia. This study aims to investigate the efficacy of combined treatment with SFN in patients with schizophrenia who experience negative symptoms and its effect on the levels of superoxide dismutase (SOD) and the inflammatory marker, high-sensitivity C-reactive protein (HsCRP).

Background-Aware Classification Activation Map for Weakly Supervised Object Localization.

Weakly supervised object localization (WSOL) relaxes the requirement of dense annotations for object localization by using image-level annotation to supervise the learning process. However, most WSOL methods only focus on forcing the object classifier to produce high activation score on object parts without considering the influence of background locations, causing excessive background activations and ill-pose background score searching. Based on this point, our work proposes a novel mechanism called the background-aware classification activation map (B-CAM) to add background awareness for WSOL training.

Power Law in Deep Neural Networks: Sparse Network Generation and Continual Learning With Preferential Attachment.

Training deep neural networks (DNNs) typically requires massive computational power. Existing DNNs exhibit low time and storage efficiency due to the high degree of redundancy. In contrast to most existing DNNs, biological and social networks with vast numbers of connections are highly efficient and exhibit scale-free properties indicative of the power law distribution, which can be originated by preferential attachment in growing networks.

Weighted Network Density Predicts Range of Latent Variable Model Accuracy.

Current experimental techniques impose spatial limits on the number of neuronal units that can be recorded invivo. To model the neuronal dynamics utilizing these sampled data, Latent Variable Models (LVMs) have been proposed to study the common unobserved processes within the system that drives neuronal activities, through an implicit network with hidden states. Yet, relationships between these latent variable models and widely-studied network connectivity measures have remained unclear.

Cross-frequency information transfer from EEG to EMG in grasping.

This paper presents an investigation into the cortico-muscular relationship during a grasping task by evaluating the information transfer between EEG and EMG signals. Information transfer was computed via a non-linear model-free measure, transfer entropy (TE). To examine the cross-frequency interaction, TEs were computed after the times series were decomposed into various frequency ranges via wavelet transform.

Effective connectivity matrix for neural ensembles.

In this paper, we present an efficient framework to study the directional interactions within the multiple-input multiple-output (MIMO) biological neural network from spiketrain data. We used an efficient generalized linear model (GLM) with Laguerre basis functions to model a MIMO neural system, and developed an Effective Connectivity Matrix (ECM) to visualize excitatory and inhibitory connections within the neural network. A new causality representation was developed based on system dynamics.

Evaluating the Small-World-Ness of a Sampled Network: Functional Connectivity of Entorhinal-Hippocampal Circuitry.

The amount of publicly accessible experimental data has gradually increased in recent years, which makes it possible to reconsider many longstanding questions in neuroscience. In this paper, an efficient framework is presented for reconstructing functional connectivity using experimental spike-train data. A modified generalized linear model (GLM) with L1-norm penalty was used to investigate 10 datasets.

Reconstruction of neural network topology using spike train data: Small-world features of hippocampal network.

As the amount of experimental data made publicly accessible has gradually increased in recent years, it is now possible to reconsider many of the longstanding questions in neuroscience. In this paper, we present an efficient frame-work for reconstructing the functional connectivity from the spike train data curated from the Collaborative Research in Computational Neuroscience (CRCNS) program. We used a modified generalized linear model (GLM) framework with L1 norm penalty to investigate 10 datasets.