Max Dabagia,Christos H Papadimitriou,Santosh S Vempala
Max Dabagia
Even as machine learning exceeds human-level performance on many applications, the generality, robustness, and rapidity of the brain's learning capabilities remain unmatched. How cognition arises from neural activity is the central open que...
Latent Space Bayesian Optimization With Latent Data Augmentation for Enhanced Exploration [0.03%]
基于潜在数据增强的潜在空间贝叶斯优化以增强探索能力
Onur Boyar,Ichiro Takeuchi
Onur Boyar
Latent space Bayesian optimization (LSBO) combines generative models, typically variational autoencoders (VAE), with Bayesian optimization (BO), to generate de novo objects of interest. However, LSBO faces challenges due to the mismatch bet...
Orthogonal Gated Recurrent Unit With Neumann-Cayley Transformation [0.03%]
基于Neumann-Cayley变换的正交门控循环神经网络
Vasily Zadorozhnyy,Edison Mucllari,Cole Pospisil et al.
Vasily Zadorozhnyy et al.
In recent years, using orthogonal matrices has been shown to be a promising approach to improving recurrent neural networks (RNNs) with training, stability, and convergence, particularly to control gradients. While gated recurrent unit (GRU...
Realizing Synthetic Active Inference Agents, Part II: Variational Message Updates [0.03%]
合成主动推理代理的实现（第二部分）：变分消息更新
Thijs van de Laar,Magnus Koudahl,Bert de Vries
Thijs van de Laar
The free energy principle (FEP) describes (biological) agents as minimizing a variational free energy (FE) with respect to a generative model of their environment. Active inference (AIF) is a corollary of the FEP that describes how agents e...
Petr Anokhin,Artyom Sorokin,Mikhail Burtsev et al.
Petr Anokhin et al.
Associative learning is a behavioral phenomenon in which individuals develop connections between stimuli or events based on their co-occurrence. Initially studied by Pavlov in his conditioning experiments, the fundamental principles of lear...
KLIF: An Optimized Spiking Neuron Unit for Tuning Surrogate Gradient Function [0.03%]
KLIF：一种用于调整代理梯度函数的优化脉冲神经元单元
Chunming Jiang,Yilei Zhang
Chunming Jiang
Spiking neural networks (SNNs) have garnered significant attention owing to their adeptness in processing temporal information, low power consumption, and enhanced biological plausibility. Despite these advantages, the development of effici...
ℓ 1 -Regularized ICA: A Novel Method for Analysis of Task-Related fMRI Data [0.03%]
L1正则化ICA：一种分析任务相关fMRI数据的新方法
Yusuke Endo,Koujin Takeda
Yusuke Endo
We propose a new method of independent component analysis (ICA) in order to extract appropriate features from high-dimensional data. In general, matrix factorization methods including ICA have a problem regarding the interpretability of ext...
Valentin Leplat,Le T K Hien,Akwum Onwunta et al.
Valentin Leplat et al.
Deep nonnegative matrix factorization (deep NMF) has recently emerged as a valuable technique for extracting multiple layers of features across different scales. However, all existing deep NMF models and algorithms have primarily centered t...
Wilka Carvalho,Momchil S Tomov,William de Cothi et al.
Wilka Carvalho et al.
Adaptive behavior often requires predicting future events. The theory of reinforcement learning prescribes what kinds of predictive representations are useful and how to compute them. This review integrates these theoretical ideas with work...
Hayden McAlister,Anthony Robins,Lech Szymanski
Hayden McAlister
We discuss prototype formation in the Hopfield network. Typically, Hebbian learning with highly correlated states leads to degraded memory performance. We show that this type of learning can lead to prototype formation, where unlearned stat...