RESUMEN
Generative models are powerful tools for producing novel information by learning from example data. However, the current approaches require explicit manual input to steer generative models to match human goals. Furthermore, how these models would integrate implicit, diverse feedback and goals of multiple users remains largely unexplored. Here, we present a first-of-its-kind system that produces novel images of faces by inferring human goals directly from cross-subject brain signals while study subjects are looking at example images. We report on an experiment where brain responses to images of faces were recorded using electroencephalography in 30 subjects, focusing on specific salient visual features (VFs). Preferences toward VFs were decoded from subjects' brain responses and used as implicit feedback for a generative adversarial network (GAN), which generated new images of faces. The results from a follow-up user study evaluating the presence of the target salient VFs show that the images generated from brain feedback represent the goal of the study subjects and are comparable to images generated with manual feedback. The methodology provides a stepping stone toward humans-in-the-loop image generation.
RESUMEN
Visual recognition requires inferring the similarity between a perceived object and a mental target. However, a measure of similarity is difficult to determine when it comes to complex stimuli such as faces. Indeed, people may notice someone "looks like" a familiar face, but find it hard to describe on the basis of what features such a comparison is based. Previous work shows that the number of similar visual elements between a face pictogram and a memorized target correlates with the P300 amplitude in the visual evoked potential. Here, we redefine similarity as the distance inferred from a latent space learned using a state-of-the-art generative adversarial neural network (GAN). A rapid serial visual presentation experiment was conducted with oddball images generated at varying distances from the target to determine how P300 amplitude related to GAN-derived distances. The results showed that distance-to-target was monotonically related to the P300, showing perceptual identification was associated with smooth, drifting image similarity. Furthermore, regression modeling indicated that while the P3a and P3b sub-components had distinct responses in location, time, and amplitude, they were similarly related to target distance. The work demonstrates that the P300 indexes the distance between perceived and target image in smooth, natural, and complex visual stimuli and shows that GANs present a novel modeling methodology for studying the relationships between stimuli, perception, and recognition.
Asunto(s)
Electroencefalografía , Potenciales Evocados Visuales , Humanos , Procesamiento de Imagen Asistido por Computador/métodosRESUMEN
Brain-computer interfaces enable active communication and execution of a pre-defined set of commands, such as typing a letter or moving a cursor. However, they have thus far not been able to infer more complex intentions or adapt more complex output based on brain signals. Here, we present neuroadaptive generative modelling, which uses a participant's brain signals as feedback to adapt a boundless generative model and generate new information matching the participant's intentions. We report an experiment validating the paradigm in generating images of human faces. In the experiment, participants were asked to specifically focus on perceptual categories, such as old or young people, while being presented with computer-generated, photorealistic faces with varying visual features. Their EEG signals associated with the images were then used as a feedback signal to update a model of the user's intentions, from which new images were generated using a generative adversarial network. A double-blind follow-up with the participant evaluating the output shows that neuroadaptive modelling can be utilised to produce images matching the perceptual category features. The approach demonstrates brain-based creative augmentation between computers and humans for producing new information matching the human operator's perceptual categories.
RESUMEN
The human brain processes language to optimise efficient communication. Studies have shown extensive evidence that the brain's response to language is affected both by lower-level features, such as word-length and frequency, and syntactic and semantic violations within sentences. However, our understanding on cognitive processes at discourse level remains limited: How does the relationship between words and the wider topic one is reading about affect language processing? We propose an information theoretic model to explain cognitive resourcing. In a study in which participants read sentences from Wikipedia entries, we show information gain, an information theoretic measure that quantifies the specificity of a word given its topic context, modulates word-synchronised brain activity in the EEG. Words with high information gain amplified a slow positive shift in the event related potential. To show that the effect persists for individual and unseen brain responses, we furthermore show that a classifier trained on EEG data can successfully predict information gain from previously unseen EEG. The findings suggest that biological information processing seeks to maximise performance subject to constraints on information capacity.
Asunto(s)
Encéfalo/fisiología , Alfabetización Informacional , Lectura , Área Bajo la Curva , Interpretación Estadística de Datos , Potenciales Evocados , Femenino , Humanos , Masculino , Modelos TeóricosRESUMEN
The use of implicit relevance feedback from neurophysiology could deliver effortless information retrieval. However, both computing neurophysiologic responses and retrieving documents are characterized by uncertainty because of noisy signals and incomplete or inconsistent representations of the data. We present the first-of-its-kind, fully integrated information retrieval system that makes use of online implicit relevance feedback generated from brain activity as measured through electroencephalography (EEG), and eye movements. The findings of the evaluation experiment (N = 16) show that we are able to compute online neurophysiology-based relevance feedback with performance significantly better than chance in complex data domains and realistic search tasks. We contribute by demonstrating how to integrate in interactive intent modeling this inherently noisy implicit relevance feedback combined with scarce explicit feedback. Although experimental measures of task performance did not allow us to demonstrate how the classification outcomes translated into search task performance, the experiment proved that our approach is able to generate relevance feedback from brain signals and eye movements in a realistic scenario, thus providing promising implications for future work in neuroadaptive information retrieval (IR).
RESUMEN
Finding relevant information from large document collections such as the World Wide Web is a common task in our daily lives. Estimation of a user's interest or search intention is necessary to recommend and retrieve relevant information from these collections. We introduce a brain-information interface used for recommending information by relevance inferred directly from brain signals. In experiments, participants were asked to read Wikipedia documents about a selection of topics while their EEG was recorded. Based on the prediction of word relevance, the individual's search intent was modeled and successfully used for retrieving new relevant documents from the whole English Wikipedia corpus. The results show that the users' interests toward digital content can be modeled from the brain signals evoked by reading. The introduced brain-relevance paradigm enables the recommendation of information without any explicit user interaction and may be applied across diverse information-intensive applications.