Jiahong Zhang

Jiahong Zhang, Yonggui Zhu, Wenshu Yu et al.

Recently, convolutional neural networks (CNNs) have been widely used in image denoising. Existing methods benefited from residual learning and achieved high performance. Much research has been paid attention to optimizing the network architecture of CNN but ignored the limitations of residual learning. This paper suggests two limitations of it. One is that residual learning focuses on estimating noise, thus overlooking the image information. The other is that the image self-similarity is not effectively considered. This paper proposes a compositional denoising network (CDN), whose image information path (IIP) and noise estimation path (NEP) will solve the two problems, respectively. IIP is trained by an image-to-image way to extract image information. For NEP, it utilizes the image self-similarity from the perspective of training. This similarity-based training method constrains NEP to output a similar estimated noise distribution for different image patches with a specific kind of noise. Finally, image information and noise distribution information will be comprehensively considered for image denoising. Experiments show that CDN achieves state-of-the-art results in synthetic and real-world image denoising. Our code will be released on https://github.com/JiaHongZ/CDN.

Jiahong Zhang, Meijun Qu, Ye Wang et al.

Recently, convolutional neural networks (CNNs) and attention mechanisms have been widely used in image denoising and achieved satisfactory performance. However, the previous works mostly use a single head to receive the noisy image, limiting the richness of extracted features. Therefore, a novel CNN with multiple heads (MH) named MHCNN is proposed in this paper, whose heads will receive the input images rotated by different rotation angles. MH makes MHCNN simultaneously utilize features of rotated images to remove noise. To integrate these features effectively, we present a novel multi-path attention mechanism (MPA). Unlike previous attention mechanisms that handle pixel-level, channel-level, or patch-level features, MPA focuses on features at the image level. Experiments show MHCNN surpasses other state-of-the-art CNN models on additive white Gaussian noise (AWGN) denoising and real-world image denoising. Its peak signal-to-noise ratio (PSNR) results are higher than other networks, such as BRDNet, RIDNet, PAN-Net, and CSANN. The code is accessible at https://github.com/JiaHongZ/MHCNN.

Ke Liu, Kaifan Yang, Jiahong Zhang et al.

Superconductivity allows electrical current to flow without any energy loss, and thus making solids superconducting is a grand goal of physics, material science, and electrical engineering. More than 16 Nobel Laureates have been awarded for their contribution to superconductivity research. Superconductors are valuable for sustainable development goals (SDGs), such as climate change mitigation, affordable and clean energy, industry, innovation and infrastructure, and so on. However, a unified physics theory explaining all superconductivity mechanism is still unknown. It is believed that superconductivity is microscopically due to not only molecular compositions but also the geometric crystal structure. Hence a new dataset, S2S, containing both crystal structures and superconducting critical temperature, is built upon SuperCon and Material Project. Based on this new dataset, we propose a novel model, S2SNet, which utilizes the attention mechanism for superconductivity prediction. To overcome the shortage of data, S2SNet is pre-trained on the whole Material Project dataset with Masked-Language Modeling (MLM). S2SNet makes a new state-of-the-art, with out-of-sample accuracy of 92% and Area Under Curve (AUC) of 0.92. To the best of our knowledge, S2SNet is the first work to predict superconductivity with only information of crystal structures. This work is beneficial to superconductivity discovery and further SDGs. Code and datasets are available in https://github.com/zjuKeLiu/S2SNet

Jiahong Zhang, Lihong Cao, Moning Zhang et al.

Backpropagation-based supervised learning has achieved great success in computer vision tasks. However, its biological plausibility is always controversial. Recently, the bio-inspired Hebbian learning rule (HLR) has received extensive attention. Self-Organizing Map (SOM) uses the competitive HLR to establish connections between neurons, obtaining visual features in an unsupervised way. Although the representation of SOM neurons shows some brain-like characteristics, it is still quite different from the neuron representation in the human visual cortex. This paper proposes an improved SOM with multi-winner, multi-code, and local receptive field, named mlSOM. We observe that the neuron representation of mlSOM is similar to the human visual cortex. Furthermore, mlSOM shows a sparse distributed representation of objects, which has also been found in the human inferior temporal area. In addition, experiments show that mlSOM achieves better classification accuracy than the original SOM and other state-of-the-art HLR-based methods. The code is accessible at https://github.com/JiaHongZ/mlSOM.

Jiahong Zhang, Lihong Cao, Qiuxia Lai et al.

The partially occluded image recognition (POIR) problem has been a challenge for artificial intelligence for a long time. A common strategy to handle the POIR problem is using the non-occluded features for classification. Unfortunately, this strategy will lose effectiveness when the image is severely occluded, since the visible parts can only provide limited information. Several studies in neuroscience reveal that feature restoration which fills in the occluded information and is called amodal completion is essential for human brains to recognize partially occluded images. However, feature restoration is commonly ignored by CNNs, which may be the reason why CNNs are ineffective for the POIR problem. Inspired by this, we propose a novel brain-inspired feature restoration network (BIFRNet) to solve the POIR problem. It mimics a ventral visual pathway to extract image features and a dorsal visual pathway to distinguish occluded and visible image regions. In addition, it also uses a knowledge module to store object prior knowledge and uses a completion module to restore occluded features based on visible features and prior knowledge. Thorough experiments on synthetic and real-world occluded image datasets show that BIFRNet outperforms the existing methods in solving the POIR problem. Especially for severely occluded images, BIRFRNet surpasses other methods by a large margin and is close to the human brain performance. Furthermore, the brain-inspired design makes BIFRNet more interpretable.

Kexin Wang, Jiahong Zhang, Yong Ren et al.

Brain-inspired Spiking Neural Network (SNN) has demonstrated its effectiveness and efficiency in vision, natural language, and speech understanding tasks, indicating their capacity to "see", "listen", and "read". In this paper, we design \textbf{SpikeVoice}, which performs high-quality Text-To-Speech (TTS) via SNN, to explore the potential of SNN to "speak". A major obstacle to using SNN for such generative tasks lies in the demand for models to grasp long-term dependencies. The serial nature of spiking neurons, however, leads to the invisibility of information at future spiking time steps, limiting SNN models to capture sequence dependencies solely within the same time step. We term this phenomenon "partial-time dependency". To address this issue, we introduce Spiking Temporal-Sequential Attention STSA in the SpikeVoice. To the best of our knowledge, SpikeVoice is the first TTS work in the SNN field. We perform experiments using four well-established datasets that cover both Chinese and English languages, encompassing scenarios with both single-speaker and multi-speaker configurations. The results demonstrate that SpikeVoice can achieve results comparable to Artificial Neural Networks (ANN) with only 10.5 energy consumption of ANN.

Negin Ashrafi, Armin Abdollahi, Jiahong Zhang et al.

Heart failure affects millions of people worldwide, significantly reducing quality of life and leading to high mortality rates. Despite extensive research, the relationship between heart failure and mortality rates among ICU patients is not fully understood, indicating the need for more accurate prediction models. This study analyzed data from 1,177 patients over 18 years old from the MIMIC-III database, identified using ICD-9 codes. Preprocessing steps included handling missing data, removing duplicates, treating skewness, and using oversampling techniques to address data imbalances. Through rigorous feature selection using Variance Inflation Factor (VIF), expert clinical input, and ablation studies, 46 key features were identified to enhance model performance. Our analysis compared several machine learning models, including Logistic Regression, Support Vector Machine (SVM), Random Forest, LightGBM, and XGBoost. XGBoost emerged as the superior model, achieving a test AUC-ROC of 0.9228 (95\% CI 0.8748 - 0.9613), significantly outperforming our previous work (AUC-ROC of 0.8766) and the best results reported in existing literature (AUC-ROC of 0.824). The improved model's success is attributed to advanced feature selection methods, robust preprocessing techniques, and comprehensive hyperparameter optimization through Grid-Search. SHAP analysis and feature importance evaluations based on XGBoost highlighted key variables like leucocyte count and RDW, providing valuable insights into the clinical factors influencing mortality risk. This framework offers significant support for clinicians, enabling them to identify high-risk ICU heart failure patients and improve patient outcomes through timely and informed interventions.

Han Xu, Xuerui Qiu, Baiyu Chen et al.

Current Large Language Models (LLMs) are primarily based on large-scale dense matrix multiplications. Inspired by the brain's information processing mechanism, we explore the fundamental question: how to effectively integrate the brain's spiking-driven characteristics into LLM inference. Spiking Neural Networks (SNNs) possess spike-driven characteristics, and some works have attempted to combine SNNs with Transformers. However, achieving spike-driven LLMs with billions of parameters, relying solely on sparse additions, remains a challenge in the SNN field. To address the issues of limited representational capacity and sparsity in existing spike encoding schemes at the LLM level, we propose SDLLM, a spike-driven large language model that eliminates dense matrix multiplications through sparse addition operations. Specifically, we use the plug-and-play gamma-SQP two-step spike encoding method to ensure that the quantization process aligns with the model's semantic space, mitigating representation degradation caused by binary spikes. Furthermore, we introduce bidirectional encoding under symmetric quantization and membrane potential clipping mechanisms, leading to spike trains with no or low firing counts dominating, significantly reducing the model's spike firing rate, while halving the number of time steps. Experimental results show that SDLLM not only significantly reduces inference costs but also achieves state-of-the-art task performance under the spike-based paradigm. For example, compared to previous spike-based LLMs, SDLLM reduces energy consumption by 7x and improves accuracy by 4.2%. Our model provides inspiration for the architecture design of the next generation of event-driven neuromorphic chips.

Han Xu, Zhiyong Qin, Di Shang et al.

Multimodal Large Language Models (MLLMs) have achieved remarkable progress but incur substantial computational overhead and energy consumption during inference, limiting deployment in resource-constrained environments. Spiking Neural Networks (SNNs), with their sparse event-driven computation, offer inherent energy efficiency advantages on neuromorphic hardware, yet extending them to MLLMs faces two key challenges: heterogeneous modalities make uniform spike encoding insufficient, and high-resolution image inputs amplify timestep unfolding overhead. We propose SpikeMLLM, the first spike-based framework for MLLMs, which unifies existing ANN quantization methods in the spiking representation space and incorporates Modality-Specific Temporal Scales (MSTS) guided by Modality Evolution Discrepancy (MED) and Temporally Compressed LIF (TC-LIF) for timestep compression from T=L-1 to T=log2(L)-1. Experiments on four representative MLLMs across diverse multimodal benchmarks show that SpikeMLLM maintains near-lossless performance under aggressive timestep compression (Tv/Tt=3/4), with average gaps of only 0.72% and 1.19% relative to the FP16 baseline on InternVL2-8B and Qwen2VL-72B. We further develop a dedicated RTL accelerator tailored to the spike-driven datapath, observing 9.06x higher throughput and 25.8x better power efficiency relative to an FP16 GPU baseline under a deployment-oriented co-design setting, suggesting the promise of algorithm-hardware co-design for efficient multimodal intelligence.