Vision transformers (ViTs) have recently obtained success in many applications, but their intensive computation and heavy memory usage at both training and inference time limit their generalization. Previous compression algorithms usually start from the pre-trained dense models and only focus on efficient inference, while time-consuming training is still unavoidable. In contrast, this paper points out that the million-scale training data is redundant, which is the fundamental reason for the tedious training. To address the issue, this paper aims to introduce sparsity into data and proposes an end-to-end efficient training framework from three sparse perspectives, dubbed Tri-Level E-ViT. Specifically, we leverage a hierarchical data redundancy reduction scheme, by exploring the sparsity under three levels: number of training examples in the dataset, number of patches (tokens) in each example, and number of connections between tokens that lie in attention weights. With extensive experiments, we demonstrate that our proposed technique can noticeably accelerate training for various ViT architectures while maintaining accuracy. Remarkably, under certain ratios, we are able to improve the ViT accuracy rather than compromising it. For example, we can achieve 15.2% speedup with 72.6% (+0.4) Top-1 accuracy on Deit-T, and 15.7% speedup with 79.9% (+0.1) Top-1 accuracy on Deit-S. This proves the existence of data redundancy in ViT. Our code is released at https://github.com/ZLKong/Tri-Level-ViT

As one of the most promising future fundamental devices, memristor has its unique advantage on implementing low-power high-speed matrix multiplication. Taking advantage of the high performance on basic matrix operation and flexibilitys of memristor crossbars, in this paper, we investigate both discrete Fourier transformation (DFT) and miltiple-input and multi-output (MIMO) detection unit in baseband processor. We reformulate the signal processing algorithms and model structures into a matrix-based framework, and present a memristor crossbar based DFT module design and MIMO detector module design. For both designs, experimental results demonstrate significant gains in speed and power efficiency compared with traditional CMOS-based designs.

Deep-learning algorithms hold promise in processing physiological signal data, including electrocardiograms (ECGs) and electroencephalograms (EEGs). However, healthcare often requires long-term monitoring, posing a challenge to traditional deep-learning models. These models are generally trained once and then deployed, which limits their ability to adapt to the dynamic and evolving nature of healthcare scenarios. Continual learning—known for its adaptive learning capabilities over time—offers a promising solution to these challenges. However, there remains an absence of consolidated literature, which reviews the techniques, applications, and challenges of continual learning specific to physiological signal analysis, as well as its future directions. Bridging this gap, our review seeks to provide an overview of the prevailing techniques and their implications for smart healthcare. We delineate the evolution from traditional approaches to the paradigms of continual learning. We aim to offer insights into the challenges faced and outline potential paths forward. Our discussion emphasizes the need for benchmarks, adaptability, computational efficiency, and user-centric design in the development of future healthcare systems.

The conventional lottery ticket hypothesis (LTH) claims that there exists a sparse subnetwork within a dense neural network and a proper random initialization method, called the winning ticket, such that it can be trained from scratch to almost as good as the dense counterpart. Meanwhile, the research of LTH in vision transformers (ViTs) is scarcely evaluated. In this paper, we first show that the conventional winning ticket is hard to find at weight level of ViTs by existing methods. Then, we generalize the LTH for ViTs to input data consisting of image patches inspired by the input dependence of ViTs. That is, there exists a subset of input image patches such that a ViT can be trained from scratch by using only this subset of patches and achieve similar accuracy to the ViTs trained by using all image patches. We call this subset of input patches the winning tickets, which represent a significant amount of information in the input data. We use a ticket selector to generate the winning tickets based on the informativeness of patches for various types of ViT, including DeiT, LV-ViT, and Swin Transformers. The experiments show that there is a clear difference between the performance of models trained with winning tickets and randomly selected subsets, which verifies our proposed theory. We elaborate the analogical similarity between our proposed Data-LTH-ViTs and the conventional LTH for further verifying the integrity of our theory. The Source codes are available at https://github.com/shawnricecake/vit-lottery-ticket-input.

When deep neural network (DNN) is extensively utilized for edge AI (Artificial Intelligence), for example, the Internet of things (IoT) and autonomous vehicles, it makes CMOS (Complementary Metal Oxide Semiconductor)-based conventional computers suffer from overly large computing loads. Memristor-based devices are emerging as an option to conduct computing in memory for DNNs to make them faster, much more energy efficient, and accurate. Despite having excellent properties, the memristor-based DNNs are yet to be commercially available because of Stuck-At-Fault (SAF) defects. A Mapping Transformation (MT) method is proposed in this paper to mitigate Stuck-at-Fault (SAF) defects from memristor-based DNNs. First, the weight distribution for the VGG8 model with the CIFAR10 dataset is presented and analyzed. Then, the MT method is used for recovering inference accuracies at 0.1% to 50% SAFs with two typical cases, SA1 (Stuck-At-One): SA0 (Stuck-At-Zero) = 5:1 and 1:5, respectively. The experiment results show that the MT method can recover DNNs to their original inference accuracies (90%) when the ratio of SAFs is smaller than 2.5%. Moreover, even when the SAF is in the extreme condition of 50%, it is still highly efficient to recover the inference accuracy to 80% and 21%. What is more, the MT method acts as a regulator to avoid energy and latency overhead generated by SAFs. Finally, the immunity of the MT Method against non-linearity is investigated, and we conclude that the MT method can benefit accuracy, energy, and latency even with high non-linearity LTP = 4 and LTD = −4.