On the visual analytic intelligence of neural networks
Stanisław Woźniak1, Hlynur Jónsson2,3, Giovanni Cherubini2
1IBM Research - Zurich, Säumerstrasse 4, 8803, Rüschlikon, Switzerland. stw@zurich.ibm.com.
Nature Communications
|September 25, 2023
Summary
We developed a biologically inspired AI system for abstract spatial reasoning, outperforming conventional models in accuracy and efficiency. This approach mimics brain function for better artificial intelligence development.
Area of Science:
- Cognitive Science
- Artificial Intelligence
- Neuroscience
Background:
- Current artificial intelligence (AI) struggles with abstract tasks like spatial reasoning.
- Existing AI models often use non-biologically-plausible architectures and are energy-intensive.
- The human brain's efficiency in reasoning offers a model for AI development.
Purpose of the Study:
- To investigate universal, ethnic-independent analytic intelligence through a visual oddity task.
- To develop a biologically inspired AI system for spatial concept comprehension.
- To compare the performance of the novel system against conventional AI architectures.
Main Methods:
- A novel visual oddity task dataset was procedurally generated.
- A biologically inspired neural network, mimicking neocortical neuron dynamics and synthetic saccades, was designed.
- The proposed system and conventional relational networks were trained and compared on the dataset.
Main Results:
- Both AI approaches demonstrated high accuracy in abstract problem-solving.
- A shared underlying reasoning mechanism was identified in both architectures.
- The biologically inspired network achieved superior accuracy, faster learning, and required fewer parameters.
Conclusions:
- Biologically inspired AI systems offer a more efficient and effective approach to abstract reasoning.
- Mimicking neural dynamics and sensory processing can enhance AI capabilities.
- This work provides insights into the mechanisms of analytic intelligence in both humans and AI.
Related Concept Videos
01:26Visual System
613
Light enters the eye through the cornea, a transparent, dome-shaped surface covering the surface of the eyeball that helps to direct and focus incoming light. This light is then channeled toward the pupil, an adjustable opening whose size is controlled by the iris. The iris, a pigmented muscle, regulates the amount of light entering the eye by contracting or dilating the pupil, thereby ensuring optimal light levels for clear vision.
Once through the pupil, the light passes through the lens, a...
Once through the pupil, the light passes through the lens, a...
613
01:24Vision
53.5K
Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
53.5K
01:25Neural Circuits
1.3K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
1.3K
01:14Motor and Sensory Areas of the Cortex
4.0K
The cerebral cortex, the brain's outermost layer, is pivotal in processing complex cognitive tasks, emotions, and various sensory inputs and executing voluntary motor activities. This intricate structure is divided into three primary functional areas: the motor areas, sensory areas, and association areas.
Motor Areas
The motor areas located in the frontal lobe are central to controlling voluntary movements. This region is further subdivided into the primary motor cortex and the premotor cortex....
Motor Areas
The motor areas located in the frontal lobe are central to controlling voluntary movements. This region is further subdivided into the primary motor cortex and the premotor cortex....
4.0K
01:12Visual Agnosia
225
Visual agnosia is a condition characterized by the inability to recognize visually presented objects despite having normal vision. For instance, a person with visual agnosia can describe the shape and color of an object but cannot identify or name it. This impairment does not affect their visual field, acuity, color vision, brightness discrimination, language, or memory. An example of this condition in a social setting is someone at a dinner party asking for "that silver thing with a round...
225
01:20Parallel Processing
173
The brain processes sensory information rapidly due to parallel processing, which involves sending data across multiple neural pathways at the same time. This method allows the brain to manage various sensory qualities, such as shapes, colors, movements, and locations, all concurrently. For instance, when observing a forest landscape, the brain simultaneously processes the movement of leaves, the shapes of trees, the depth between them, and the various shades of green. This enables a quick and...
173