Better, But Not Sufficient: Testing Video ANNs Against Macaque IT Dynamics
Feedforward artificial neural networks (ANNs) trained on static images remain the dominant models of the the primate ventral visual stream, yet they are intrinsically limited to static computations. The primate world is dynamic, and the macaque ventral visual pathways, specifically the inferior temporal (IT) cortex not only supports object recognition but also encodes object motion velocity during naturalistic video viewing. Does IT's temporal responses reflect nothing more than time-unfolded feedforward transformations, framewise features with shallow temporal pooling, or do they embody richer dynamic computations? We tested this by comparing macaque IT responses during naturalistic videos against static, recurrent, and video-based ANN models. Video models provided modest improvements in neural predictivity, particularly at later response stages, raising the question of what kind of dynamics they capture. To probe this, we applied a stress test: decoders trained on naturalistic videos were evaluated on "appearance-free" variants that preserve motion but remove shape and texture. IT population activity generalized across this manipulation, but all ANN classes failed. Thus, current video models better capture appearance-bound dynamics rather than the appearance-invariant temporal computations expressed in IT, underscoring the need for new objectives that encode biological temporal statistics and invariances.
Code (0)
등록된 구현이 없습니다.
Tasks
Object RecognitionSimilar Papers 제목 키워드 기반
Biologically inspired sleep algorithm for increased generalization and adversarial robustness in deep neural networks
Current artificial neural networks (ANNs) can perform and excel at a variety of tasks ranging from image classification to spam detection through training on large datasets of labeled data. While the trained network may …
Adversarial RobustnessGeneral Classificationimage-classificationImage Classification+1Normalized gradient flow optimization in the training of ReLU artificial neural networks
The training of artificial neural networks (ANNs) is nowadays a highly relevant algorithmic procedure with many applications in science and industry. Roughly speaking, ANNs can be regarded as iterated compositions betwee…
The necessity of depth for artificial neural networks to approximate certain classes of smooth and bounded functions without the curse of dimensionality
In this article we study high-dimensional approximation capacities of shallow and deep artificial neural networks (ANNs) with the rectified linear unit (ReLU) activation. In particular, it is a key contribution of this w…
Neural Networks for Infectious Diseases Detection: Prospects and Challenges
Artificial neural network (ANN) ability to learn, correct errors, and transform a large amount of raw data into useful medical decisions for treatment and care have increased its popularity for enhanced patient safety an…
DiagnosticTesting the Tools of Systems Neuroscience on Artificial Neural Networks
Neuroscientists apply a range of common analysis tools to recorded neural activity in order to glean insights into how neural circuits implement computations. Despite the fact that these tools shape the progress of the f…