Related papers: MIND: Maximum Mutual Information Based Neural Deco…
Natural spatiotemporal processes can be highly non-stationary in many ways, e.g. the low-level non-stationarity such as spatial correlations or temporal dependencies of local pixel values; and the high-level variations such as the…
The mutual information is bounded from above by a decreasing affine function of the square of the distance between the input distribution and the set of all capacity-achieving input distributions $\Pi_{\mathcal{A}}$, on small enough…
Motor imagery (MI) is a well-documented technique used by subjects in BCI (Brain Computer Interface) experiments to modulate brain activity within the motor cortex and surrounding areas of the brain. In our term project, we conducted an…
Sequence-to-sequence neural translation models learn semantic and syntactic relations between sentence pairs by optimizing the likelihood of the target given the source, i.e., $p(y|x)$, an objective that ignores other potentially useful…
In this work, we propose an information theory based framework DeepMI to train deep neural networks (DNN) using Mutual Information (MI). The DeepMI framework is especially targeted but not limited to the learning of real world tasks in an…
We present SEED (Semantic Evaluation for Visual Brain Decoding), a novel metric for evaluating the semantic decoding performance of visual brain decoding models. It integrates three complementary metrics, each capturing a different aspect…
Lip reading has received an increasing research interest in recent years due to the rapid development of deep learning and its widespread potential applications. One key point to obtain good performance for the lip reading task depends…
Existing rumor detection methods often neglect the content within images as well as the inherent relationships between contexts and images across different visual scales, thereby resulting in the loss of critical information pertinent to…
Masked Image Modeling (MIM) achieves outstanding success in self-supervised representation learning. Unfortunately, MIM models typically have huge computational burden and slow learning process, which is an inevitable obstacle for their…
We propose a novel optimization-based decoding algorithm for LDPC-coded massive MIMO channels. The proposed decoding algorithm is based on a proximal gradient method for solving an approximate maximum a posteriori (MAP) decoding problem.…
This work investigates online learning techniques for a cognitive radar network utilizing feedback from a central coordinator. The available spectrum is divided into channels, and each radar node must transmit in one channel per time step.…
Masked image modeling (MIM) with transformer backbones has recently been exploited as a powerful self-supervised pre-training technique. The existing MIM methods adopt the strategy to mask random patches of the image and reconstruct the…
Estimating and optimizing Mutual Information (MI) is core to many problems in machine learning; however, bounding MI in high dimensions is challenging. To establish tractable and scalable objectives, recent work has turned to variational…
The human brain is a complex system requiring both macroscopic and microscopic components for comprehensive understanding. However, mapping nonlinear relationships between these scales remains challenging due to technical limitations and…
Recent advancements in multi-modal large language models have propelled the development of joint probabilistic models capable of both image understanding and generation. However, we have identified that recent methods suffer from loss of…
End-to-end autoencoder (AE) learning has the potential of exceeding the performance of human-engineered transceivers and encoding schemes, without a priori knowledge of communication-theoretic principles. In this work, we aim to understand…
Stimulus dimensionality-reduction methods in neuroscience seek to identify a low-dimensional space of stimulus features that affect a neuron's probability of spiking. One popular method, known as maximally informative dimensions (MID), uses…
Recently, several methods have been proposed for estimating the mutual information from sample data using deep neural networks and without the knowing closed form distribution of the data. This class of estimators is referred to as neural…
Obtaining meaningful quantitative descriptions of the statistical dependence within multivariate systems is a difficult open problem. Recently, the Partial Information Decomposition (PID) was proposed to decompose mutual information (MI)…
Multiple Instance Learning is the predominant method for Whole Slide Image classification in digital pathology, enabling the use of slide-level labels to supervise model training. Although MIL eliminates the tedious fine-grained annotation…