• BrainCog on the Cover of Patterns Volume. 4 Issue. 8, 2023 from Cell Press, and officially published, 10 years of development on BrainCog, and get ready for the future of BrainCog towards AGI for good!
• The BrainCog paper is out! A summary and updates for a 10 years' development of BrainCog and its future. Check it here.
• A keynote talk titled "Building and Living with Brain-inspired Ethical AI" for the vision and progress of BrainCog at Foundations and Applications of Artificial Intelligence 2022.
• A recent talk on "Brain-inspired Artificial Intelligence-Towards Brain-inspired Conscious Living Becomings" reflects the progresses for the BrainCog project.
• Brain-inspired Cognitive Intelligence Engine (BrainCog) and related efforts was reported in Artificial Intelligence in China series in the China News program on the International Channel of China Central Television.
• CASIA Brain Simulation System : Check out our recent efforts on multi-scale brain simulation based on BrainCog.

• N-Omniglot: A Large-scale Neuromorphic Dataset for Spatio-Temporal Sparse Few-shot Learning.
• Bullying10K: A Neuromorphic Dataset towards Privacy-Preserving Bullying Recognition

• BrainCog integrates neuronal computational models at different levels of granularity, multiple brain-inspired learning and plasticity principles, and different types of neural network connectivity patterns and encoding strategies.
• Towards AI application intelligent models, BrainCog realizes multiple brain-inspired cognitive functions based on Spiking Neural Networks that can be classified into five categories: Perception and Learning, Decision Making, Motor Control, Knowledge Representation, and Reasoning, and Social Cognition. These components collectively form neural circuits corresponding to 28 brain areas in the mammalian brains.
• Brain-inspired learning mechanism: We combine the local and global plasticity, and propose a more biologically plausible spiking neural network with feedforward and feedback connections. The biologically plausible spatio-temporal adjustment algorithm based on BrainCog can theoretically achieve competitive classification accuracy with only about 3% of the energy compared with artificial neural networks of the same structure. The ANN-SNN conversion model built based on BrainCog fully combines the advantages of backpropagation algorithm and SNN, enabling SNN to perform image classification and target detection tasks almost losslessly with 1/10 and 1/50 of the simulation time of other algorithms. The unsupervised SNN model based on the STDP algorithm supported by BrainCog achieves the best performance among STDP-based unsupervised algorithms to date by integrating biologically plausible optimization algorithm and various adaptive mechanisms, while achieving superior performance than ANN by 4%-5% under the same model structure with an extremely small number of samples.
• Social cognition spiking neural network models empower humanoid robots to perceive and understand themselves and others in order to pass the MultiRobots Mirror Self-Recognition Test, and help other agents avoid potential risks, showing preliminary ethical-like behavior.
• BrainCog provides structure simulations of different mammalian brains at multiple scales, builds the mouse brain simulator that includes different types of point neurons, monkey brain simulator (1.21 billion spiking neurons, 1.3 trillion synapses, 1/5 of macaque brain scale) and human brain simulator (860 million spiking neurons, 2.5 trillion synapses, 1/100 of human brain scale).
• The BORN, an Artificial Intelligence Engine based on BrainCog, could perform the emotion-dependent music composition and play by humanoid robot.

Brain-inspired Cognitive Intelligence Engine (BrainCog) integrates multi-scale biological plausible plasticity principles, supports Spiking Neural Network based brain-inspired Artificial Intelligence modeling, and brain function and structure simulation. BrainCog provides complete and systematic interface components for researchers in brain-inspired AI and computational neuroscience.

• Spiking Neuron models with different levels of granularity: BrainCog not only contains the commonly used Integrate-and-Fire (IF), Leaky Integrate-and-Fire (LIF) spiking neuron, but also incorporates Hodgkin-Huxley (H-H), Izhikevich and other neuronal models commonly used in the field of computational neuroscience and brain stimulation.
• Multiple brain-inspired learning and plasticity principles: biologically plausible plasticity principles such as Hebbian, Spike-Timing-Dependent Plasticity (STDP), Short-term Synaptic Plasticity (STP), and surrogate gradient-based SNN backpropagation algorithms and conversion based on well pre-trained ANN.
• Different connectivity patterns for SNNs: e.g., lateral inhibition, local connectivity, feedforward connectivity, feedback connectivity, etc.
• Different encoding strategies: e.g. rate coding, temporal coding, population coding, etc.
• Multiple SNN models of functional brain regions: based on the above components, BrainCog constructs several Spiking Neural Network computational models of functional brain regions such as prefrontal cortex (PFC), hippocampus, basal ganglia, thalamus, visual pathway, motor cortex, etc.

BrainCog allows researchers to freely design their own network and the corresponding functions by calling and connecting the essential modules. For Brain-inspired AI, BrainCog collaborates with multiple brain regions to form different neural circuits and preliminarily implements five categories of cognitive functions: Perception and Learning, Decision Making, Motor Control, Knowledge Representation and Reasoning, and Social Cognition. BrainCog also realizes partial brain cognitive function simulation, as well as the structure and mechanism simulation of different biological brain from multiple scales. Currently, the field of brain-inspired spiking neural networks lacks an open, fair platform to evaluate the performance of algorithms in the same environment. BrainCog integrates multiple high-performance, easy-to-modify SNN models that have been effectively validated on various benchmark tasks. Users can evaluate their own algorithms in the same environment and compare them with other methods. You can also easily implement your own algorithms using the components provided by BrainCog and compare them fairly with other state-of-the-art methods.

BrainCog is aimed at providing infrastructural support for specialized, generalized Brain-inspired AI. Currently, it provides cognitive function components that can be classified into five categories: Perception and Learning, Decision Making, Motor Control, Knowledge Representation and Reasoning, and Social Cognition. These components collectively form neural circuits corresponding to 28 brain areas in the mammalian brains. These brain-inspired AI models have been effectively validated on various supervised and unsupervised learning, deep reinforcement learning, and several complex brain-inspired cognitive tasks.

BrainCog provides a variety of supervised and unsupervised methods for training spiking neural networks, such as the biologically-plausible Spike Timing-Dependent Plasticity (STDP), the backpropagation based on surrogate gradients, and the conversion-based algorithms. In addition to high performance in common perception and learning process, it also shows strong adaptability in small samples and noisy scenarios. BrainCog also provides a multi-sensory integration framework for human-like concept learning.

• The SNN with the combination of feedforward and feedback connections implemented by BrainCog, which introduces a global error signal through feedback connections, improves the performance and stability of local optimization rule-based SNN on deep network structures, achieving comparable performance with the backpropagation algorithm.
• Biologically Plausible Spatio-Temporal Adjustment algorithm implemented by BrainCog enables training of deep SNN models and demonstrates advanced performance and low energy consumption compared to other SNNs for image classification tasks such as MNIST, CIFAR10, ImageNet, and event classification tasks such as DVS-CIFAR10 and DVS-Gesture.
• The ANN-SNN conversion model based on BrainCog fully combines the advantages of backpropagation algorithm and SNN, enabling SNN to perform comparably to ANN in tasks such as image classification, target detection and semantic segmentation with less energy consumption and higher efficiency.
• The unsupervised SNN model based on STDP constructed using BrainCog greatly improves the network performance and efficiency by integrating biologically plausible optimization algorithm and various adaptive mechanisms. It achieves better performance than ANN with the same model structure under a small number of samples.

BrainCog provides multi-brain areas coordinated decision-making SNN model and deep reinforcement learning SNN.

• BrainCog implements a biologically plausible brain-inspired decision-making SNN model and achieves human-like learning ability on the Flappy bird game and has the ability to support online decision-making for UAVs, enabling Drosophila-inspired linear and nonlinear decision making and reversal learning.
• The Spiking-DQN model built on BrainCog implements a combination of deep SNN and reinforcement learning and achieves better performance compared with traditional DQN model on Atari games.

BrainCog has preliminarily implemented control of the motion of humanoid robots by spiking neural network.

• Inspired by the brain motor control mechanism, we construct a multi-brain areas coordinated robot motor SNN model that incorporates premotor cortex (PMC), supplementary motor area (SMA), basal ganglia and cerebellar functions, and apply to a humanoid robot playing the piano.

BrainCog performs knowledge representation and reasoning by incorporating multi-neural plasticity and population coding mechanisms.

• Brain-inspired music memory and stylistic composition SNN model achieves knowledge representation and memory of musical note sequences, and can generate melody with different styles. Sequence Production SNN achieves the representation and memory of symbol sequences and can reconstruct symbol sequences according to different rules.
• Commonsense Knowledge Representation Graph SNN encodes the commonsense knowledge base into a SNN, whereby the network can complete conceptual knowledge generation and other cognitive tasks. Causal Reasoning SNN encodes causal graphs into SNN, and realizes cognitive tasks such as deductive reasoning and abductive reasoning.

BrainCog implements a biologically plausible brain-inspired social cognitive spiking neural network model.

• This model gives the agent a preliminary ability to perceive and understand itself and others and can enable the robots to pass the multi-robots mirror self-recognition test, and help other agents avoid potential risks.
• The former is a classic experiment of self-perception in social cognition, and the latter is a variation and application of the theory of mind experiment in social cognition.

BrainCog can support simulations of brain structure and cognitive function at different scales, thus providing powerful support for computationally validating scientific conjectures and scientific explanations from local and whole brain scales.

BrainCog realizes Drosophila linear and nonlinear decision-making and prefrontal cortex (PFC) working memory function simulation.

• For Drosophila linear and nonlinear decision-making simulation, BrainCog verifies the winner-takes-all behaviors of the nonlinear decision-making circuit under a dilemma and obtains consistent conclusions with Drosophila biological experiments. The corresponding algorithm enables UAVs to achieve brain-inspired decision-making ability.
• For the working memory performance of the prefrontal cortex network implemented by BrainCog, we discover that using human neurons to replace rodent neurons without changing network structure can significantly improve the accuracy and completeness of an image memory task, and this implies the evolution of the brains are not only on their structures, but also applies to single computational units such as neurons.

BrainCog provides simulations of brain structures at different scales, from microcircuits, and cortical columns, to whole-brain structure simulations. Anatomical and imaging multi-scale connectivity data is used to support whole-brain simulations from mouse brain, macaque brain to human brain at different scales.

Brain-inspired Artificial Intelligence
• Wenxuan Pan, Feifei Zhao, Zhuoya Zhao, Yi Zeng. Brain-inspired Evolutionary Architectures for Spiking Neural Networks. IEEE Transactions on Artificial Intelligence, 2024.
• Yang Li, Xiang He, Qingqun Kong, Yi Zeng. Spiking Neural Networks with Consistent Mapping Relations Allow High-Accuracy Inference. Information Sciences, 2024.
• Linghao Feng, Dongcheng Zhao, Yi Zeng. Spiking generative adversarial network with attention scoring decoding. Neural Networks, 2024.
• Yiting Dong, Xiang He, Guobin Shen, Dongcheng Zhao, Yang Li, Yi Zeng. EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Vision. arXiv preprint arXiv: 2405.18880 (2024).
• Zhuoya Zhao, Feifei Zhao, Shiwen Wang, Yinqian Sun, Yi Zeng. A Brain-inspired Theory of Collective Mind Model for Efficient Social Cooperation. IEEE Transactions on Artificial Intelligence, 2024.
• Xiang He, Yang Li, Dongcheng Zhao, Qingqun Kong, Yi Zeng. MSAT: biologically inspired multistage adaptive threshold for conversion of spiking neural networks. Neural Computing and Applications, 2024.
• Xiang He, Dongcheng Zhao, Yang Li, Guobin Shen, Qingqun Kong, Yi Zeng. An Efficient Knowledge Transfer Strategy for Spiking Neural Networks from Static to Event Domain. Proceedings of the AAAI Conference on Artificial Intelligence, 2024.
• Jindong Li, Guobin Shen, Dongcheng Zhao, Qian Zhang, Yi Zeng. Firefly v2: Advancing hardware support for high-performance spiking neural network with a spatiotemporal fpga accelerator. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2024
• Yao Liang, Yuwei Wang, Yang Li, Yi Zeng. Matrix-Transformation Based Low-Rank Adaptation (MTLoRA): A Brain-Inspired Method for Parameter-Efficient Fine-Tuning. arXiv preprint arXiv: 2403.07440 (2024).
• Yiting Dong, Dongcheng Zhao, Yi Zeng. Temporal knowledge sharing enable spiking neural network learning from past and future. IEEE Transactions on Artificial Intelligence, 2024
• Yi Zeng, Feifei Zhao, Yuxuan Zhao, Dongcheng Zhao, Enmeng Lu, Qian Zhang, Yuwei Wang, Hui Feng, Zhuoya Zhao, Jihang Wang, Qingqun Kong, Yinqian Sun, Yang Li, Guobin Shen, Bing Han, Yiting Dong, Wenxuan Pan, Xiang He, Aorigele Bao, Jin Wang. Brain-inspired and Self-based Artificial Intelligence. arXiv preprint arXiv: 2402.18784 (2024).
• Yang Li, Yinqian Sun, Xiang He, Yiting Dong, Dongcheng Zhao, Yi Zeng. Parallel Spiking Unit for Efficient Training of Spiking Neural Networks. IJCNN, 2024.
• Guobin Shen, Dongcheng Zhao, Yi Zeng. Exploiting nonlinear dendritic adaptive computation in training deep Spiking Neural Networks. Neural Networks, 2024.
• Guobin Shen, Dongcheng Zhao, Tenglong Li, Jindong Li, Yi Zeng. Are Conventional SNNs Really Efficient? A Perspective from Network Quantization.. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024.
• Jindong Li, Tenglong Li, Guobin Shen, Dongcheng Zhao, Qian Zhang, Yi Zeng. Revealing Untapped DSP Optimization Potentials for FPGA-Based Systolic Matrix Engines. 34th International Conference on Field-Programmable Logic and Applications, 2024.
• Sicheng Shen, Dongcheng Zhao, Guobin Shen, Yi Zeng. TIM: An Efficient Temporal Interaction Module for Spiking Transformer. IJCAI, 2024.
• Yiting Dong, Yang Li, Dongcheng Zhao, Guobin Shen, Yi Zeng. Bullying10K: A Large-Scale Neuromorphic Dataset towards Privacy-Preserving Bullying Recognition. Advances in Neural Information Processing Systems, 2024, 36.
• Guobin Shen, Dongcheng Zhao, Xiang He, Linghao Feng, Yiting Dong, Jihang Wang, Qian Zhang, Yi Zeng. Neuro-Vision to Language: Image Reconstruction and Language enabled Interaction via Brain Recordings. arXiv preprint arXiv: 2404.19438 (2024).
• Wenxuan Pan, Feifei Zhao, Bing Han, Yiting Dong, Yi Zeng. Emergence of brain-inspired small-world spiking neural network through neuroevolution. iScience, Cell Press, 2024.
• Guobin Shen, Dongcheng Zhao, Yiting Dong, Yang Li, Jindong Li, Kang Sun, Yi Zeng. Astrocyte-Enabled Advancements in Spiking Neural Networks for Large Language Modeling. Arxiv, 2023.
• Yuxuan Zhao, Enmeng Lu, Yi Zeng. Brain-inspired bodily self-perception model for robot rubber hand illusion. Patterns, Cell Press, 2023.
• Guobin Shen, Dongcheng Zhao, Yiting Dong, Yi Zeng. Brain-inspired neural circuit evolution for spiking neural networks. Proceedings of the National Academy of Sciences (PNAS), 2023.
• Wenxuan Pan, Feifei Zhao, Yi Zeng, Bing Han. Adaptive structure evolution and biologically plausible synaptic plasticity for recurrent spiking neural networks. Scientific Reports, Nature Press, 2023.
• Yi Zeng, Dongcheng Zhao, Feifei Zhao, Guobin Shen, Yiting Dong, Enmeng Lu, Qian Zhang, Yinqian Sun, Qian Liang, Yuxuan Zhao, Zhuoya Zhao, Hongjian Fang, Yuwei Wang, Yang Li, Xin Liu, Chengcheng Du, Qingqun Kong, Zizhe Ruan, Weida Bi. BrainCog: A Spiking Neural Network based Brain-inspired Cognitive Intelligence Engine for Brain-inspired AI and Brain Simulation. Patterns, Cell Press, 2023.
• Yiting Dong, Dongcheng Zhao, Yang Li, Yi Zeng. An unsupervised STDP-based spiking neural network inspired by biologically plausible learning rules and connections. Neural Networks, 165:799-808, 2023.
• Jindong Li, Guobin Shen, Dongcheng Zhao, Qian Zhang, Yi Zeng. FireFly: A High-Throughput Hardware Accelerator for Spiking Neural Networks With Efficient DSP and Memory Optimization. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2023.
• Zhuoya Zhao, Feifei Zhao, Yuxuan Zhao, Yi Zeng, Yinqian Sun. A brain-inspired theory of mind spiking neural network improves multi-agent cooperation and competition, Patterns, Cell Press, 2023.
• Guobin Shen, Dongcheng Zhao, Yi Zeng. EventMix: An efficient data augmentation strategy for event-based learning, Information Sciences, Volume 644, 119170, October 2023.
• Jinyu Fan, Yi Zeng. Challenging Deep Learning Models with Image Distortion Based on the Abutting Grating Illusion, Patterns, Cell Press, 2023.
• Yang Li, Yiting Dong, Dongcheng Zhao, Yi Zeng. N-Omniglot: a Large-scale Neuromorphic Dataset for Spatio-temporal Sparse Few-shot Learning. Scientific Data, 9(746), Nature Publishing Group, 2022.
• Feifei Zhao, Yi Zeng, Bing Han, Hongjian Fang, Zhuoya Zhao. Nature-inspired Self-organizing Collision Avoidance for Drone Swarm Based on Reward-modulated Spiking Neural Network, Patterns, Cell Press, 2022.
• Hui Feng, Yi Zeng. A Brain-Inspired Robot Pain Model Based on a Spiking Neural Network, Frontiers in Neurorobotics, 2022.
• Yinqian Sun, Yi Zeng, and Yang Li. Solving the Spike Feature Information Vanishing Problem in Spiking Deep Q Network with Potential Based Normalization, Frontiers in Neuroscience, 2022.
• Yuxuan Zhao, Yi Zeng. A Brain-inspired Intention Prediction Model and Its Applications to Humanoid Robot, Frontiers in Neuroscience, 16:1009237, 2022.
• Yang Li, Dongcheng Zhao, and Yi Zeng. BSNN: Towards Faster and Better Conversion of Artificial Neural Networks to Spiking Neural Networks with Bistable Neurons, Frontiers in Neuroscience, 2022.
• Hui Feng, Yi Zeng, and Enmeng Lu. Brain-Inspired Affective Empathy Computational Model and Its Application on Altruistic Rescue Task, Frontiers in Computational Neuroscience, 2022.
• Dongcheng Zhao, Yi Zeng, Yang Li, Jihang Wang, Qian Zhang. Spiking Capsnet: A Spiking Neural Network With a Biologically Plausible Routing Rule Between Capsules, Information Sciences, 2022.
• Dongcheng Zhao, Yi Zeng, Yang Li. BackEISNN: A Deep Spiking Neural Network with Adaptive Self-Feedback and Balanced Excitatory-Inhibitory Neurons, Neural Networks, Volume 154, 68-77, 2022.
• Guobin Shen, Dongcheng Zhao, Yi Zeng. Backpropagation with Biologically Plausible Spatiotemporal Adjustment for Training Deep Spiking Neural Networks. Patterns, Cell Press, 2022.
• Zhuoya Zhao, Enmeng Lu, Feifei Zhao, Yi Zeng, and Yuxuan Zhao. A Brain-Inspired Theory of Mind Spiking Neural Network for Reducing Safety Risks of Other Agents. Frontiers in Neuroscience, 2022.
• Yang Li, Yi Zeng. Efficient and Accurate Conversion of Spiking Neural Network with Burst Spikes. Proceedings of the 31st International Joint Conferences on Artificial Intelligence (IJCAI-22), 2022.
• Yuwei Wang, Yi Zeng. Multisensory Concept Learning Framework Based on Spiking Neural Networks. Frontiers in Systems Neuroscience, 16:845177, 2022.
• Yuwei Wang, Yi Zeng. Statistical Analysis of Multisensory and Text-Derived Representations on Concept Learning. Frontiers in Computational Neuroscience, 16:861265, 2022.
• Hongjian Fang, Yi Zeng. A Brain-Inspired Causal Reasoning Model Based on Spiking Neural Networks. 2021 International Joint Conference on Neural Networks (IJCNN). IEEE, 2021.
• Yinqian Sun, Yi Zeng, Tielin Zhang. Quantum Superposition Inspired Spiking Neural Network. iScience, 24(8), 102880, Cell Press, 2021.
• Yuxuan Zhao, Yi Zeng, Guang Qiao. Brain-Inspired Classical Conditioning Model. iScience, 24(1), 101980, Cell Press, 2021.
• Yang Li, Yiting Dong, Dongcheng Zhao, Yi Zeng. N-Omniglot: a Large-scale Neuromorphic Dataset for Spatio-Temporal Sparse Few-shot Learning. Arxiv:2112.13230, 2021.
• Feifei Zhao, Yi Zeng, Jun Bai. Toward a Brain-Inspired Developmental Neural Network Based on Dendritic Spine Dynamics. Neural Computation, MIT Press, 2021.
• Qian Liang, Yi Zeng. Stylistic Composition of Melodies based on a Brain-inspired Spiking Neural Network. Frontiers in Systems Neuroscience, 15:639484, 2021.
• Feifei Zhao, Yi Zeng. Dynamically Optimizing Network Structure Based on Synaptic Pruning in the Brain. Frontiers in Systems Neuroscience, 15:620558, 2021.
• Hongjian Fang, Yi Zeng, Feifei Zhao. Brain Inspired Sequences Production by Spiking Neural Networks With Reward-Modulated STDP. Frontiers in Computational Neuroscience, 15:612041, 2021.
• Dongcheng Zhao, Yi Zeng, Tielin Zhang, Mengting Shi, Feifei Zhao. GLSNN: A Multi-layer Spiking Neural Network based on Global Feedback Alignment and Local STDP Plasticity. Frontiers in Computational Neuroscience, 2020.
• Yi Zeng, Yuxuan Zhao, Tielin Zhang, Dongcheng Zhao, Feifei Zhao, and Enmeng Lu. A Brain-Inspired Model of Theory of Mind. Frontiers in Neurorobotics, 2020.
• Qian Liang, Yi Zeng, Bo Xu. Temporal-Sequential Learning with a Brain-Inspired Spiking Neural Network and Its Application to Musical Memory. Frontiers in Computational Neuroscience, 14:51, 2020.
• Feifei Zhao, Qingqun Kong, Yi Zeng, Bo Xu. A Brain-inspired Visual Fear Responses Model for UAV Emergent Obstacle Dodging. IEEE Transactions on Cognitive and Developmental Systems, 12(1): 124-132, 2020.
• Yuwei Wang, Yi Zeng, Jianbo Tang and Bo Xu. Biological Neuron Coding Inspired Binary Word Embeddings. Cognitive Computation, Springer, 2019.
• Dongcheng Zhao, Yi Zeng. Dynamic Fusion of Convolutional Features based on Spatial and Temporal Attention for Visual Tracking. Proceedings of the 2019 International Joint Conference on Neural Networks (IJCNN 2019). Budapest, Hungary, July 14-19, 2019.
• Feifei Zhao, Yi Zeng, and Bo Xu. A Brain-inspired Decision-Making Spiking Neural Network and Its Application in Unmanned Aerial Vehicle. Frontiers in Neurorobotics, 2018.
• Yi Zeng, Guixiang Wang, Bo Xu. A Basal Ganglia Network Centric Reinforcement Learning Model and Its Application in Unmanned Aerial Vehicle. IEEE Transactions on Cognitive and Developmental Systems, 10(2): 290-303, 2018.
• Yi Zeng, Yuxuan Zhao, Jun Bai, Bo Xu. Towards Robot Self-consciousness (II): Brain-inspired Robot Bodily Self Model for Self-Recognition. Cognitive Computation, 10(2): 307-320, Springer, 2018.
• Yi Zeng, Tielin Zhang, Bo Xu. Improving Multi-layer Spiking Neural Networks by Incorporating Brain-inspired Rules. SCIENCE CHINA Information Sciences, 60(5): 052201, 2017.
• Feifei Zhao, Tielin Zhang, Yi Zeng, Bo Xu. Towards a Brain-inspired Developmental Neural Network by Adaptive Synaptic Pruning. Proceedings of the 24th International Conference on Neural Information Processing (ICONIP 2017), 2017.
• Guang Qiao, Hongyue Du, Yi Zeng. A Quaternionic Rate-based Synaptic Learning Rule Derived from Spike-Timing Dependent Plasticity. Lecture Notes in Computer Science, 10261, 457-465, 2017.
• Xin Liu, Yi Zeng, Bo Xu. Parallel Brain Simulator: A Multi-scale and Parallel Brain-inspired Neural Network Modeling and Simulation Platform. Cognitive Computation, Volume 8, Issue 5, 967-981, Springer, 2016.
• Yi Zeng, Yuxuan Zhao, Jun Bai. Towards Robot Self-Consciousness (I): Brain-inspired Robot Mirror Neuron System Model and Its Application in Mirror Self-Recognition. Lecture Notes in Computer Science, 10023, 11-21, 2016.
• Guixiang Wang, Yi Zeng, Bo Xu. A Spiking Neural Network Based Autonomous Reinforcement Learning Model and Its Application in Decision Making. Lecture Notes in Computer Science, 10023, 125-137, 2016.
• Yi Zeng, Chenglin Liu, Tieniu Tan. Retrospect and Outlook of Brain-inspired Intelligence Research [in Chinese]. The Chinese Journal of Computers, Volume 39, Issue 1, 212-222, 2016.
• Bo Xu, Chenglin Liu, Yi Zeng. Research Status and Developments of Brain-inspired Intelligence [in Chinese]. Bulletin of Chinese Academy of Sciences, Volume 31, Issue 7, 793-802, 2016.
• Yi Zeng, Feifei Zhao, Guixiang Wang, Lingyu Zhang, Bo Xu. Brain-inspired Obstacle Detection based on the Biological Visual Pathway. Proceedings of the 2016 International Conference on Brain Informatics and Health, Lecture Notes in Artificial Intelligence 9919, Omaha, Nebraska, USA, 2016.
• Yuwei Wang, Yi Zeng, Bo Xu. SHTM: A Neocortex-inspired Algorithm for One-shot Text Generation. Proceedings of the 2016 IEEE International Conference on Systems, Man, and Cybernetics, 898-903, IEEE Press, Budapest, Hungary, October 9-12, 2016.
• Xiaomei kang, Qingqun Kong, Yi Zeng, Bo Xu. A Fast Contour Detection Model Inspired by Biological Mechanisms in Primary Vision System. Frontiers in Computational Neuroscience, 2018.
• Feifei Zhao, Yi Zeng, Guixiang Wang, Jun Bai, Bo Xu. A Brain-inspired Decision Making Model based on Top-down Biasing of Prefrontal Cortex to Basal Ganglia and Its Application in Autonomous UAV Explorations. Cognitive Computation, 10(2): 296-306, Springer, 2018.
• Qingqun Kong, Yi Zeng, Qiulei Dong. Biologically Inspired Deep Stereo Model. Proceedings of the 2015 IEEE International Conference on Image Processing (ICIP 2015), 3700-3704, Quebec City, Canada, 2015.
Brain Simulation
• Qian Zhang, Han Lu, jihang Wang, Taoyi Yang, Weida Bi, Yi Zeng, Buwei Yu. Hierarchical rhythmic propagation of corticothalamic interactions for consciousness: A computational study. Computers in Biology and Medicine, 2023.
• Qian Zhang, Yi Zeng, Tielin Zhang, Taoyi Yang. Comparison Between Human and Rodent Neurons for Persistent Activity Performance: A Biologically Plausible Computational Investigation. Frontiers in System Neuroscience, 2021.
• Feifei Zhao, Yi Zeng, Aike Guo, Haifeng Su, Bo Xu. A Neural Algorithm for Drosophila Linear and Nonlinear Decision-making. Scientific Reports, 10: 18660, Nature Publishing Group, 2020.
• Qian Zhang, Yi Zeng, Taoyi Yang. Computational Investigation of Contributions from Different Subtypes of Interneurons in Prefrontal Cortex for Information Maintenance. Scientific Reports, 10: 4671, Nature Publishing Group, 2020.
• Qingqun Kong, Jiuqi Han, Yi Zeng, Bo Xu. Efficient Coding Matters in the Organization of the Early Visual System. Neural Networks, Elsevier, 2018.
• Yi Zeng, Tielin Zhang, Bo Xu. Neural Pathway Prediction based on Multi-neuron Spike Train Data. The Twenty-Third Annual Computational Neuroscience Meeting (CNS 2014), Québec City, Canada, July 26-31, 2014, BMC Neuroscience, 15(Suppl 1): P6, 2014.
• Jiuqi Han, Qingqun Kong, Yi Zeng and Hongwei Hao. HEVS: A Hierarchical Computational Model for Early Stages of the Visual System. Proceedings of the 2015 International Joint Conference on Neural Networks (IJCNN 2015), 1-8, Killarney, Ireland, July 12-17, 2015.
• Yi Zeng, Weida Bi, Yun Wang, Xuan Tang and Bo Xu. Automatic Recovery of Z-Jumps for Neuronal Morphology Reconstruction. Frontiers in Neuroinformatics. Conference Abstract: The 7th Neuroinformatics Congress (Neuroinformatics 2014), Leiden, the Netherlands, August 25-27, 2014.
• Yi Zeng, Weida Bi, Xuan Tang, and Bo Xu. Neuronal Morphology Modeling Based on Microscopy Reconstruction Data in the Public Repositories. Proceedings of the 2014 International Conference on Brain Informatics and Health (BIH 2014), Lecture Notes in Artificial Intelligence 8609, 1-11, Springer, Warsaw, Poland, August 11-14, 2014.

• Principal Investigator: Yi Zeng
• Team Members: Dongcheng Zhao, Feifei Zhao, Guobin Shen, Yiting Dong, Enmeng Lu, Qian Zhang, Yinqian Sun, Qian Liang, Yuxuan Zhao, Zhuoya Zhao, Hongjian Fang, Yuwei Wang, Yang Li, Xin Liu, Chengcheng Du, Qingqun Kong, Zizhe Ruan, Weida Bi, cunqing huangfu, jinyu fan, xuan tang, taoyi yang, hui feng, linghao feng, bing han, wenxuan pan, mengyue cai, xiang he, jindong li, weiyi li, yao liang, jihang wang, qianhao wang