Strong and Precise Modulation of Human Percepts via Robustified ANNs
The visual object category reports of artificial neural networks (ANNs) are notoriously sensitive to tiny, adversarial image perturbations. Because human category reports (aka human percepts) are thought to be insensitive to those same small-norm perturbations -- and locally stable in general -- this argues that ANNs are incomplete scientific models of human visual perception. Consistent with this, we show that when small-norm image perturbations are generated by standard ANN models, human object category percepts are indeed highly stable. However, in this very same "human-presumed-stable" regime, we find that robustified ANNs reliably discover low-norm image perturbations that strongly disrupt human percepts. These previously undetectable human perceptual disruptions are massive in amplitude, approaching the same level of sensitivity seen in robustified ANNs. Further, we show that robustified ANNs support precise perceptual state interventions: they guide the construction of low-norm image perturbations that strongly alter human category percepts toward specific prescribed percepts. In sum, these contemporary models of biological visual processing are now accurate enough to guide strong and precise interventions on human perception.
Code (1)
Similar Papers 제목 키워드 기반
Robustified ANNs Reveal Wormholes Between Human Category Percepts
The visual object category reports of artificial neural networks (ANNs) are notoriously sensitive to tiny, adversarial image perturbations. Because human category reports (aka human percepts) are thought to be insensitiv…
Sim-to-Real Transfer Learning using Robustified Controllers in Robotic Tasks involving Complex Dynamics
Learning robot tasks or controllers using deep reinforcement learning has been proven effective in simulations. Learning in simulation has several advantages. For example, one can fully control the simulated environment,…
Deep Reinforcement LearningFrictionReinforcement LearningTransfer LearningDelving Deeper into Convolutional Networks for Learning Video Representations
We propose an approach to learn spatio-temporal features in videos from intermediate visual representations we call "percepts" using Gated-Recurrent-Unit Recurrent Networks (GRUs).Our method relies on percepts that are e…
Action RecognitionDecoderTemporal Action LocalizationVideo CaptioningDeepNose: An Equivariant Convolutional Neural Network Predictive Of Human Olfactory Percepts
The olfactory system employs responses of an ensemble of odorant receptors (ORs) to sense molecules and to generate olfactory percepts. Here we hypothesized that ORs can be viewed as 3D spatial filters that extract molec…
Unsupervised Online Grounding of Natural Language during Human-Robot Interactions
Allowing humans to communicate through natural language with robots requires connections between words and percepts. The process of creating these connections is called symbol grounding and has been studied for nearly th…