05 2023 档案

Uncovering the Representation of Spiking Neural Networks Trained with Surrogate Gradient
摘要:郑重声明:原文参见标题,如有侵权,请联系作者,将会撤销发布! Published in Transactions on Machine Learning Research (04/2023) Abstract 脉冲神经网络(SNN)由于其生物合理性和能量效率而被认为是下一代神经网络的候选者。最近,研 阅读全文

posted @ 2023-05-28 11:28 穷酸秀才大草包 阅读(307) 评论(0) 推荐(0)

Short-Term Plasticity Neurons Learning to Learn and Forget
摘要:郑重声明:原文参见标题,如有侵权,请联系作者,将会撤销发布! Proceedings of the 39th International Conference on Machine Learning, 2022 Abstract 短期可塑性(STP)是一种将衰退记忆储存在大脑皮层突触中的机制。在计算 阅读全文

posted @ 2023-05-16 18:56 穷酸秀才大草包 阅读(290) 评论(0) 推荐(0)

Robust Deep Reinforcement Learning through Adversarial Loss
摘要:郑重声明:原文参见标题,如有侵权,请联系作者,将会撤销发布! 35th Conference on Neural Information Processing Systems (NeurIPS 2021) Abstract 最近的研究表明,深度强化学习智能体很容易受到智能体输入上的小对抗扰动的影响, 阅读全文

posted @ 2023-05-09 15:51 穷酸秀才大草包 阅读(365) 评论(0) 推荐(0)

Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations
摘要:郑重声明:原文参见标题,如有侵权,请联系作者,将会撤销发布! 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, Canada. Abstract 深度强化学习(DRL)智能体通过观察 阅读全文

posted @ 2023-05-05 11:06 穷酸秀才大草包 阅读(467) 评论(0) 推荐(0)

导航