Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
The authors investigate whether sensory-aligned receptive fields confer computational benefits beyond simple wiring efficiency by independently varying feed-forward structural alignment and single-cell complexity in recurrent networks of Expressive Leaky Memory neurons. Evaluating across auditory and neuromorphic vision tasks, they find that receptive fields aligned with task-relevant sensory coordinates consistently outperform budget-matched random connectivity, an advantage that vanishes under coordinate scrambling and cannot be fully recovered by generic L1 sparsity penalties. Crucially, scaling up individual neuronal expressivity systematically diminishes this performance gap, showing that intrinsic single-neuron computation can substitute for structured connectivity priors.
Generic sparsity cannot replicate the inductive bias of sensory-aligned receptive fields, yet high single-neuron expressivity renders such structural architectural priors largely redundant.
Biological sensory neurons have selective receptive fields organized along meaningful stimulus coordinates, such as frequency, motion direction, or retinotopic position. Such structure may arise from efficient coding and biological constraints on activity, connectivity, and wiring, as computational studies of simple neurons have shown across modalities. This raises a question: do structured receptive fields confer a computational advantage beyond resource efficiency itself, and does this advantage persist when individual neurons are highly expressive? We address this question in recurrent networks of Expressive Leaky Memory neurons, where we can independently vary neuronal complexity and the organization of feed-forward receptive fields. Across auditory and event-based visual classification tasks, receptive fields aligned with a task-relevant sensory coordinate improve test accuracy relative to budget-matched random receptive fields. This advantage disappears when sensory coordinates are scrambled, or when receptive fields follow task-irrelevant coordinates, showing that the benefit comes from alignment with task geometry rather than restricted connectivity alone. Increasing neuronal complexity reduces the performance advantage of structured receptive fields. Finally, generic synaptic sparsity regularization induces input selectivity and partially recovers performance, but remains substantially below explicitly structured receptive fields, suggesting that sparsity alone is insufficient to recover the full computational benefit of task-aligned receptive fields. Together, our results show that appropriate receptive fields can serve as a computational prior beyond sparsity itself, and that their value depends on the computational expressivity of individual neurons.