More Like this

1. Domain-specific experience determines individual differences in holistic processing

   https://doi.org/10.1037/xge0000628  

   Chua, K.-W.; Gauthier, I. (January 2020, Journal of experimental psychology)

   null (Ed.)

   Holistic processing refers to the processing of objects as wholes rather than in a piecemeal, part-based fashion. Despite a suggested link between expertise and holistic processing, the role of experience in determining holistic processing of both faces and objects has been questioned. Here, we combine an individual differences approach with an experimental training study and parametrically manipulate experience with novel objects to examine the determinants of holistic processing. We also measure object-recognition ability. Our results show that although domain-general visual ability is a predictor of the ability to match object parts, it is the amount of experience people have individuating objects of a category that determines the extent to which they process new objects of this category in a holistic manner. This work highlights the benefits of dissociating the influences of domain-general ability and domain-specific experience, typically confounded in measures of performance or “expertise.” Our findings are consistent with those in recent work with faces showing that variability specific to experience is a better predictor of domain-specific effects than is variability in performance. We argue that individual differences in holistic processing arise from domain-specific experience and that these effects are related to similar effects of experience on other measures of selective attention. 

   more » « less
2. Enhancing Working Memory Training with Transcranial Direct Current Stimulation

   https://doi.org/10.1162/jocn_a_00979  

   Au, Jacky; Katz, Benjamin; Buschkuehl, Martin; Bunarjo, Kimberly; Senger, Thea; Zabel, Chelsea; Jaeggi, Susanne M.; Jonides, John (September 2016, Journal of Cognitive Neuroscience)

   Abstract Working memory (WM) is a fundamental cognitive ability that supports complex thought but is limited in capacity. Thus, WM training interventions have become very popular as a means of potentially improving WM-related skills. Another promising intervention that has gained increasing traction in recent years is transcranial direct current stimulation (tDCS), a noninvasive form of brain stimulation that can modulate cortical excitability and temporarily increase brain plasticity. As such, it has the potential to boost learning and enhance performance on cognitive tasks. This study assessed the efficacy of tDCS to supplement WM training. Sixty-two participants were randomized to receive either right prefrontal, left prefrontal, or sham stimulation with concurrent visuospatial WM training over the course of seven training sessions. Results showed that tDCS enhanced training performance, which was strikingly preserved several months after training completion. Furthermore, we observed stronger effects when tDCS was spaced over a weekend break relative to consecutive daily training, and we also demonstrated selective transfer in the right prefrontal group to nontrained tasks of visual and spatial WM. These findings shed light on how tDCS may be leveraged as a tool to enhance performance on WM-intensive learning tasks. 

   more » « less
3. Covariate Shift Detection via Domain Interpolation Sensitivity

   Gokhale, Tejas (July 2022, First Workshop on Interpolation Regularizers and Beyond at NeurIPS 2022)

   Covariate shift is a major roadblock in the reliability of image classifiers in the real world. Work on covariate shift has been focused on training classifiers to adapt or generalize to unseen domains. However, for transparent decision making, it is equally desirable to develop covariate shift detection methods that can indicate whether or not a test image belongs to an unseen domain. In this paper, we introduce a benchmark for covariate shift detection (CSD), that builds upon and complements previous work on domain generalization. We use state-of-the-art OOD detection methods as baselines and find them to be worse than simple confidence-based methods on our CSD benchmark. We propose an interpolation-based technique, Domain Interpolation Sensitivity (DIS), based on the simple hypothesis that interpolation between the test input and randomly sampled inputs from the training domain, offers sufficient information to distinguish between the training domain and unseen domains under covariate shift. DIS surpasses all OOD detection baselines for CSD on multiple domain generalization benchmarks. 

   more » « less
4. Efficient Federated Domain Translation

   Zhou, Zeyu; Azam, Sheikh Shams; Brinton, Christopher; Inouye, David I. (January 2023, International Conference on Learning Representations)

   A central theme in federated learning (FL) is the fact that client data distributions are often not independent and identically distributed (IID), which has strong implications on the training process. While most existing FL algorithms focus on the conventional non-IID setting of class imbalance or missing classes across clients, in practice, the distribution differences could be more complex, e.g., changes in class conditional (domain) distributions. In this paper, we consider this complex case in FL wherein each client has access to only one domain distribution. For tasks such as domain generalization, most existing learning algorithms require access to data from multiple clients (i.e., from multiple domains) during training, which is prohibitive in FL. To address this challenge, we propose a federated domain translation method that generates pseudodata for each client which could be useful for multiple downstream learning tasks. We empirically demonstrate that our translation model is more resource-efficient (in terms of both communication and computation) and easier to train in an FL setting than standard domain translation methods. Furthermore, we demonstrate that the learned translation model enables use of state-of-the-art domain generalization methods in a federated setting, which enhances accuracy and robustness to increases in the synchronization period compared to existing methodology. 

   more » « less
5. DeepIsoFun: a deep domain adaptation approach to predict isoform functions

   https://doi.org/10.1093/bioinformatics/bty1017  

   Shaw, Dipan; Chen, Hao; Jiang, Tao; Hancock, John (December 2018, Bioinformatics)

   Abstract Motivation Isoforms are mRNAs produced from the same gene locus by alternative splicing and may have different functions. Although gene functions have been studied extensively, little is known about the specific functions of isoforms. Recently, some computational approaches based on multiple instance learning have been proposed to predict isoform functions from annotated gene functions and expression data, but their performance is far from being desirable primarily due to the lack of labeled training data. To improve the performance on this problem, we propose a novel deep learning method, DeepIsoFun, that combines multiple instance learning with domain adaptation. The latter technique helps to transfer the knowledge of gene functions to the prediction of isoform functions and provides additional labeled training data. Our model is trained on a deep neural network architecture so that it can adapt to different expression distributions associated with different gene ontology terms. Results We evaluated the performance of DeepIsoFun on three expression datasets of human and mouse collected from SRA studies at different times. On each dataset, DeepIsoFun performed significantly better than the existing methods. In terms of area under the receiver operating characteristics curve, our method acquired at least 26% improvement and in terms of area under the precision-recall curve, it acquired at least 10% improvement over the state-of-the-art methods. In addition, we also study the divergence of the functions predicted by our method for isoforms from the same gene and the overall correlation between expression similarity and the similarity of predicted functions. Availability and implementation https://github.com/dls03/DeepIsoFun/ Supplementary information Supplementary data are available at Bioinformatics online. 

   more » « less