Academic Journal
No One-Size-Fits-All Neurons: Task-Based Neurons for Artificial Neural Networks.
| Τίτλος: | No One-Size-Fits-All Neurons: Task-Based Neurons for Artificial Neural Networks. |
|---|---|
| Συγγραφείς: | Fan FL, Wang M, Dong HC, Ma J, Zeng T |
| Πηγή: | IEEE transactions on pattern analysis and machine intelligence [IEEE Trans Pattern Anal Mach Intell] 2026 Oct; Vol. 48 (10), pp. 13759-13766. |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: IEEE Computer Society Country of Publication: United States NLM ID: 9885960 Publication Model: Print Cited Medium: Internet ISSN: 1939-3539 (Electronic) Linking ISSN: 00985589 NLM ISO Abbreviation: IEEE Trans Pattern Anal Mach Intell Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: [New York] IEEE Computer Society. |
| Ιατρικοί όροι (MeSH): | Neurons*/physiology , Neural Networks, Computer* , Models, Neurological*, Brain/physiology ; Humans ; Algorithms ; Soft Computing |
| Περίληψη: | In the past decade, many successful networks are on novel architectures, which almost exclusively use the same type of neurons. Recently, more and more deep learning studies have been inspired by the idea of NeuroAI and the neuronal diversity observed in human brains, leading to the proposal of novel artificial neuron designs. Designing well-performing neurons represents a new dimension relative to designing well-performing neural architectures. Biologically, the brain does not rely on a single type of neuron that universally functions in all aspects. Instead, in our brain, neurons are often task-based. In this study, we address the following question: since the human brain is a task-based neuron user, can the artificial network design go from the task-based architecture design to the task-based neuron design? Since methodologically there are no one-size-fits-all neurons, given the same structure, task-based neurons can enhance the feature representation ability relative to the existing universal neurons due to the intrinsic inductive bias for the task. Specifically, we propose a two-step framework for prototyping task-based neurons. First, symbolic regression is used to identify optimal formulas that fit input data by utilizing base functions such as polynomials. We introduce vectorized symbolic regression (VSR) that stacks all variables in a vector and regularizes each input variable to perform the same computation, which can increase the regression speed, facilitate efficacy in high dimensions, and enable parallel computation. Second, we parameterize the acquired elementary formula to make parameters learnable, which serves as the aggregation function of the neuron. The activation functions such as ReLU and the sigmoidal functions remain the same because they have proven to be good. As the initial step, we evaluate the proposed framework using polynomials as base functions. Empirically, systematic experimental results on synthetic data, classic benchmarks, and real-world applications show that the proposed task-based neuron design is not only feasible but also delivers competitive performance over other state-of-the-art models. |
| Entry Date(s): | Date Created: 20260616 Date Completed: 20260924 Latest Revision: 20260925 |
| Update Code: | 20260925 |
| DOI: | 10.1109/TPAMI.2026.3704202 |
| PMID: | 42301827 |
| Βάση Δεδομένων: | MEDLINE |
καταχωρήστε σχόλιο πρώτοι!