Computational neuroscience and artificial neural network machine learning represent distinct fields with minimal theoretical overlap
the verdict
REFUTED
the evidence says no
confidence 10/100
Computational neuroscience and artificial neural network machine learning exhibit extensive theoretical and architectural overlap, with numerous studies utilizing deep learning models to simulate brain function and incorporating biological principles into artificial networks.
Evidence against · 10
Language processing in brains and deep neural networks: computational convergence and its limits
2020 · cited by 35
Yamins et al. demonstrate that deep neural networks successfully predict human brain representations and language processing.
See more details
More against · 9
Training biologically plausible recurrent neural networks on cognitive tasks with long-term dependencies
2023 · cited by 16
This study bridges computational neuroscience and recurrent neural network training to model biological cognition and memory.
Neuro-Nav: A Library for Neurally-Plausible Reinforcement Learning
2022 · cited by 10
Neuro-Nav bridges reinforcement learning from artificial intelligence with canonical behavioral and neural models in cognitive science.
MAP-SNN: Mapping spike activities with multiplicity, adaptability, and plasticity into bio-plausible spiking neural networks
2022 · cited by 5
Research on spiking neural networks explicitly incorporates biological properties like synaptic plasticity into machine learning frameworks.
A hybrid Spiking Neural Network–Transformer architecture for motor imagery and sleep apnea detection
2025 · cited by 4
Combining spiking neural networks and transformers integrates biologically plausible temporal processing with machine learning models.
Biologically plausible learning in recurrent neural networks reproduces neural dynamics observed during cognitive tasks
2016 · cited by 4
Recurrent neural networks are shown to successfully replicate complex cortical dynamics observed in animal brains during cognitive tasks.
Biologically plausible learning in a deep recurrent spiking network
2019 · cited by 4
This work develops biologically plausible deep spiking networks that approach the performance of standard artificial neural networks.
Indirect feedback alignment in deep learning for cognitive agent modeling: enhancing self-confidence analytics in the workplace
2024 · cited by 3
Indirect feedback alignment integrates biological plausibility into deep learning credit assignment for cognitive modeling.
Towards New Generation, Biologically Plausible Deep Neural Network Learning
2022 · cited by 2
Studies on biologically plausible deep neural network learning directly compare artificial learning rules with biological mechanisms.
Topology-aware design of spiking neural networks via modular graph architectures.
2026 · cited by 0
Spiking neural networks combine biologically plausible architectures with artificial neural network optimization for improved performance.