Tag
The paper introduces a self-supervised representation learning framework that uses temporal proximity as supervision to learn compact representations from short-term animal movement trajectories, showing they reveal individual identity and learning progress in freely behaving rats.
Researchers simulated a fruit fly's brain inside a world model, allowing the virtual brain to 'fly' in a simulated environment, marking a notable step in whole-brain modeling and neural emulation.
研究人员将模拟果蝇大脑接入可生成完整虚拟世界的AI系统Odyssey-3，使这个在软件中重建的生物大脑能够自主探索从未存在过的想象环境。
MIT researchers published a PNAS paper showing that artificial neural networks can build their own learning machinery through simple local rules, reshaping randomly connected units into effective information-processing networks without a developer's guiding hand, offering new insights into how the brain learns.
Task-structured modularity emerges in artificial networks and aligns with brain architecture
The article ponders whether a fully simulated fruit-fly brain could count as the first 'immortal' being, extending the thought experiment to whole-brain scanning and mind uploading into repairable robotic bodies to achieve human immortality.
A GitHub project that connects a fly's connectome neural simulation to a live Doom game arena for real-time control and experimental dopamine-gated memory rules, currently in a live training phase without demonstrated learned survival.
This paper proposes a unified dynamical framework for training, learning, and inference in neural systems.
This paper presents a computational framework for steering representational geometry to improve bidirectional alignment between biological and artificial neural networks, showing a 55% relative enhancement in bidirectional predictivity.
This paper studies how an agent with limited perceptual bandwidth should allocate interoceptive precision across bodily needs in a foraging task, showing that dynamically attending to the most-needed channel improves survival under a fixed precision budget.
This paper investigates the concept of 'ontological inversion' under the free energy principle, using a convolutional variational autoencoder to explore whether a synthetic environment can permanently replace a system's default generative model. The study finds a decoupling between representational accuracy and default behavior, introducing the phenomenon of 'cognitive relapse' where the system partially reverts to its original model.
This paper proposes replacing the standard point neuron model in artificial neural networks with a more realistic cortical cell model, claiming improvements in expressivity, robustness, learning speed, and reduced memorization and data requirements.