
- Read more about Large Dimensional Analysis of LS-SVM Transfer Learning (application on PolSAR)
- Log in to post comments
- Categories:

- Read more about Model-Free Learning of Optimal Beamformers for Passive IRS-Assisted Sumrate Maximization
- Log in to post comments
Although Intelligent Reflective Surfaces (IRSs) are a cost-effective technology promising high spectral efficiency in future wireless networks, obtaining optimal IRS beamformers is a challenging problem with several practical limitations. Assuming fully-passive, sensing- free IRS operation, we introduce a new data-driven Zeroth-order Stochastic Gradient Ascent (ZoSGA) algorithm for sumrate optimization in an IRS-aided downlink setting.
ZoSGA_Poster.pdf

- Categories:

- Read more about FAST SINGLE-PERSON 2D HUMAN POSE ESTIMATION USING MULTI-TASK CONVOLUTIONAL NEURAL NETWORKS
- Log in to post comments
This paper presents a novel neural module for enhancing existing fast and lightweight 2D human pose estimation CNNs, in order to increase their accuracy. A baseline stem CNN is augmented by a collateral module, which is tasked to encode global spatial and semantic information and provide it to the stem network during inference. The latter one outputs the final 2D human pose estimations.
- Categories:

- Read more about Designing Transformer networks for sparse recovery of sequential data using deep unfolding
- Log in to post comments
Deep unfolding models are designed by unrolling an optimization algorithm into a deep learning network. These models have shown faster convergence and higher performance compared to the original optimization algorithms. Additionally, by incorporating domain knowledge from the optimization algorithm, they need much less training data to learn efficient representations. Current deep unfolding networks for sequential sparse recovery consist of recurrent neural networks (RNNs), which leverage the similarity between consecutive signals.
- Categories:

- Read more about Designing Transformer networks for sparse recovery of sequential data using deep unfolding: Presentation
- Log in to post comments
Deep unfolding models are designed by unrolling an optimization algorithm into a deep learning network. These models have shown faster convergence and higher performance compared to the original optimization algorithms. Additionally, by incorporating domain knowledge from the optimization algorithm, they need much less training data to learn efficient representations. Current deep unfolding networks for sequential sparse recovery consist of recurrent neural networks (RNNs), which leverage the similarity between consecutive signals.
- Categories:

- Read more about Presentation Slides of "The First Pathloss Radio Map Prediction Challenge"
- Log in to post comments
To foster research and facilitate fair comparisons among recently proposed pathloss radio map prediction methods, we have launched the ICASSP 2023 First Pathloss Radio Map Prediction Challenge.
In this short overview, we briefly describe the pathloss prediction problem, the provided datasets, the challenge task and the challenge evaluation methodology. Finally, we present the results of the challenge.
- Categories:

- Read more about IMPQ: Reduced Complexity Neural Networks via Granular Precision Assignment
- Log in to post comments
- Categories:

- Read more about Mixture Model Auto-Encoders: Deep Clustering through Dictionary Learning
- Log in to post comments
mixmate.pdf

- Categories:

- Read more about Neural Collapse in Deep Homogeneous Classifiers and the Role of Weight Decay
- Log in to post comments
Neural Collapse is a phenomenon recently discovered in deep classifiers where the last layer activations collapse onto their class means, while the means and last layer weights take on the structure of dual equiangular tight frames. In this paper we present results showing the role of weight decay in the emergence of Neural Collapse in deep homogeneous networks. We show that certain near-interpolating minima of deep networks satisfy the Neural Collapse condition, and this can be derived from the gradient flow on the regularized square loss.
- Categories:

- Read more about Temporal Knowledge Distillation for On-device Audio Classification
- Log in to post comments
- Categories: