Related Experiment Video
Updated: Aug 5, 2026
11:15
Automated Visual Cognitive Tasks for Recording Neural Activity Using a Floor Projection Maze
Published on: February 20, 2014
Neural sampling from cognitive maps enables goal-directed imagination and planning
Hui Lin1,2, Yukun Yang2, Rong Zhao1
1Department of Precision Instruments, Center for Brain-Inspired Computing Research (CBICR), Tsinghua University, Beijing, China.
Nature Machine Intelligence
|July 25, 2026
Summary
Brains achieve intelligence with low energy use via cognitive maps, stochastic computing, and compositional coding. This approach enables energy-efficient AI for flexible problem-solving on edge devices.
Area of Science:
- Neuroscience and Artificial Intelligence
- Computational Neuroscience
- Energy-Efficient Computing
Background:
- Current artificial intelligence (AI) systems demand significant energy and extensive training.
- Human brains operate efficiently (20W), learn continuously, and adapt dynamically.
- Understanding brain mechanisms for intelligence is key to developing efficient AI.
Purpose of the Study:
- To investigate brain-inspired data structures, algorithms, and learning methods for AI.
- To enable artificial systems to plan and solve novel problems, mimicking brain capabilities.
- To develop energy-efficient AI solutions for edge devices.
Main Methods:
- Examined cognitive maps, stochastic computing, and compositional coding as core brain tools.
- Integrated these tools into a transparent neural network model.
- Demonstrated the model's capability for flexible planning and problem-solving.
Main Results:
- The integrated model successfully demonstrated flexible planning and problem-solving capabilities.
- The approach is suitable for energy-efficient neuromorphic hardware and in-memory computing.
- Self-supervised local synaptic plasticity enables on-chip learning.
Conclusions:
- Brain-inspired intelligence, focusing on planning and problem-solving, can be achieved without deep neural networks or large language models.
- This approach allows for the creation of energy-efficient AI for edge devices.
- Core features of brain intelligence, like solving novel problems, are transferable to artificial systems.
Related Concept Videos
01:21Cognitive Learning
Cognitive learning is based on purposive behavior, incidental learning, and insight learning.
E. C. Tolman's theory of purposive behavior emphasizes that much behavior is goal-directed. He argued that to understand behavior, we must look at the entire sequence of actions leading to a goal. For instance, high school students study hard, not just due to past reinforcement but also to achieve the goal of getting into a good college.
Tolman introduced the idea that behavior is influenced by...
E. C. Tolman's theory of purposive behavior emphasizes that much behavior is goal-directed. He argued that to understand behavior, we must look at the entire sequence of actions leading to a goal. For instance, high school students study hard, not just due to past reinforcement but also to achieve the goal of getting into a good college.
Tolman introduced the idea that behavior is influenced by...
01:23Storage
A schema is a mental framework that helps individuals organize and interpret information. Schemata, formed from previous experiences, influence how we process new information: how we encode it, the inferences we make, and how we retrieve it. For instance, a schema for what a typical classroom looks like might include desks, a teacher's desk, a whiteboard, and students in such an environment. This expectation helps us quickly understand and navigate new classrooms without needing to analyze each...