Causal Influences Decouple From Their Underlying Network Structure In Echo State Networks
Echo State Networks (ESN) are versatile recurrent neural network models in which the hidden layer remains unaltered during training. Interactions among nodes of this static backbone produce diverse representations of the given stimuli that are harnessed by a read-out mechanism to perform computations needed for solving a given task. ESNs are accessible models of neuronal circuits, since they are relatively inexpensive to train. Therefore, ESNs have become attractive for neuroscientists studying the relationship between neural structure, function, and behavior. For instance, it is not yet clear how distinctive connectivity patterns of brain networks support effective interactions among their nodes and how these patterns of interactions give rise to computation. To address this question, we employed an ESN with a biologically inspired structure and used a systematic multi-site lesioning framework to quantify the causal contribution of each node to the network's output, thus providing a causal link between network structure and behavior. We then focused on the structure-function relationship and decomposed the causal influence of each node on all other nodes, using the same lesioning framework. We found that nodes in a properly engineered ESN interact largely irrespective of the network's underlying structure. However, in a network with the same topology and a non-optimal parameter set, the underlying connectivity patterns determine the node interactions. Our results suggest that causal structure-function relations in ESNs can be decomposed into two components, direct and indirect interactions. The former are based on influences relying on structural connections. The latter describe the effective communication between any two nodes through other intermediate nodes. These widely distributed indirect interactions may crucially contribute to the efficient performance of ESNs.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Mask2Cause: Causal Discovery via Adjacency Constrained Causal Attention
Leveraging deep learning for causal discovery in time series remains challenging because existing neural methods predominantly rely on component-wise architectures that fail to capture shared system dynamics or employ de…
Temporally Disentangled Representation Learning
Recently in the field of unsupervised representation learning, strong identifiability results for disentanglement of causally-related latent variables have been established by exploiting certain side information, such as…
DisentanglementRepresentation LearningInformation Theoretic Measures of Causal Influences during Transient Neural Events
Transient phenomena play a key role in coordinating brain activity at multiple scales, however,their underlying mechanisms remain largely unknown. A key challenge for neural data science is thus to characterize the netwo…
Time SeriesTime Series AnalysisCausal Representation Learning from Multiple Distributions: A General Setting
In many problems, the measured variables (e.g., image pixels) are just mathematical functions of the latent causal variables (e.g., the underlying concepts or objects). For the purpose of making predictions in changing e…
Representation LearningSurjective Independence of Causal Influences for Local Bayesian Network Structures
The very expressiveness of Bayesian networks can introduce fresh challenges due to the large number of relationships they often model. In many domains, it is thus often essential to supplement any available data with eli…