1,721,049 research outputs found
Multi-Task Generalization and Adaptation between Noisy Digit Datasets: An Empirical Study
No full textTransfer learning for adaptation to new tasks is usually performed by either finetuning all model parameters or parameters in the final layers. We show that good target performance can also be achieved on typical domain adaptation tasks by adapting only the normalization statistics and affine transformations of layers throughout the network. We apply this adaptation scheme to supervised domain adaptation on common digit datasets and study robustness properties under perturbation by noise. Our results indicate that (1) adaptation to noise exceeds the difficulty of widely used digit benchmarks in domain adaptation,(2) the similarity of the optimal adaptation parameters for different domains is strongly predictive of generalization performance, and (3) generalization performance is highest with training on a rich environment or high noise levels
SALAD: A Toolbox for Semi-supervised Adaptive Learning Across Domains
No full textWe introduce salad, an open source toolbox that provides a unified implementation of state-of-the-art methods for transfer learning, semi-supervised learning and domain adaptation. In the first release, we provide a framework for reproducing, extending and combining research results of the past years, including model architectures, loss functions and training algorithms. The toolbox along with first benchmark results and further resources is accessible at domainadaptation.org
Multi-Task Generalization and Adaptation between Noisy Digit Datasets: An Empirical Study
No full textTransfer learning for adaptation to new tasks is usually performed by either finetuning all model parameters or parameters in the final layers. We show that good target performance can also be achieved on typical domain adaptation tasks by adapting only the normalization statistics and affine transformations of layers throughout the network. We apply this adaptation scheme to supervised domain adaptation on common digit datasets and study robustness properties under perturbation by noise. Our results indicate that (1) adaptation to noise exceeds the difficulty of widely used digit benchmarks in domain adaptation,(2) the similarity of the optimal adaptation parameters for different domains is strongly predictive of generalization performance, and (3) generalization performance is highest with training on a rich environment or high noise levels
SALAD: A Toolbox for Semi-supervised Adaptive Learning Across Domains
No full textWe introduce salad, an open source toolbox that provides a unified implementation of state-of-the-art methods for transfer learning, semi-supervised learning and domain adaptation. In the first release, we provide a framework for reproducing, extending and combining research results of the past years, including model architectures, loss functions and training algorithms. The toolbox along with first benchmark results and further resources is accessible at domainadaptation.org
On the classification of cortical inhibitory neurons
No full textThe brain's remarkable ability to process ambiguous information and transform it into meaningful behavior is a complex process largely performed by neurons. In computational neuroscience, this integration is investigated utilizing large-scale simulations constrained by realistic networks of excitatory and inhibitory neurons. In the cerebral cortex, inhibitory neurons exhibit high variability in cellular properties such as morphology, electrophysiology, and gene expression profiles. This diversity poses a challenge in terms of their characterization and classification across data modalities. While the major subtype specification of inhibitory neurons is given by their molecular identity, it is unknown whether morphological and electrophysiological properties systematically relate to molecular identity to organize the structure and function underlying cortical networks. In this dissertation, I present a computational methodology to assess variations in morphological, electrophysiological, and molecular properties across the entire depth of rat barrel cortex. First, I standardize a comprehensive dataset of morphological and electrophysiological properties, and demonstrate that it is representative for the depth distribution of inhibitory neurons in a cortical column. Then, the molecular composition of the entire rat barrel cortex is acquired, and quantified at 50-micron resolution. For each neuron, I calculate a variety of morphological and electrophysiological features. Multimodal clustering is then utilized to assign neurons into subtypes. Cross-validation with several classifiers is applied to identified subtypes, demonstrating their robustness. The proposed methodology outperforms existing approaches, and its interpretable nature allows me to reliably link different cellular properties across cortical depth. I found that the relative distributions of morphological and electrophysiological properties are similar at any given depth location. At the same time, these distributions systematically shift as a function of cortical depth. Regardless of subtype, the overall axonal and dendritic arborizations, as well as the firing frequency, increase with depth. In contrast, the firing frequency adaptation remains unaffected by depth. Surprisingly, these variations define depth-specific relationships that reveal the molecular identity of inhibitory neurons, which are conserved across species and cortex areas. Thus, simple organizing principles may largely account for the diversity of inhibitory neurons through the adjustment of their morphological and electrophysiological properties to their local environment within cortical circuits, providing novel insight for realistic network modeling
Accuracy of Rats in Discriminating Visual Objects Is Explained by the Complexity of Their Perceptual Strategy
Full text linkDespite their growing popularity as models of visual functions, it remains unclear whether rodents are capable of deploying advanced shape-processing strategies when engaged in visual object recognition. In rats, for instance, pattern vision has been reported to range from mere detection of overall object luminance to view-invariant processing of discriminative shape features. Here we sought to clarify how refined object vision is in rodents, and how variable the complexity of their visual processing strategy is across individuals. To this aim, we measured how well rats could discriminate a reference object from 11 distractors, which spanned a spectrum of image-level similarity to the reference. We also presented the animals with random variations of the reference, and processed their responses to these stimuli to derive subject-specific models of rat perceptual choices. Our models successfully captured the highly variable discrimination performance observed across subjects and object conditions. In particular, they revealed that the animals that succeeded with the most challenging distractors were those that integrated the wider variety of discriminative features into their perceptual strategies. Critically, these strategies were largely preserved when the rats were required to discriminate outlined and scaled versions of the stimuli, thus showing that rat object vision can be characterized as a transformation-tolerant, feature-based filtering process. Overall, these findings indicate that rats are capable of advanced processing of shape information, and point to the rodents as powerful models for investigating the neuronal underpinnings of visual object recognition and other high-level visual functions
Generating Spike Trains with Specified Correlation Coefficients
No full textSpike trains recorded from populations of neurons can exhibit substantial pairwise correlations between neurons and rich temporal structure. Thus, for the realistic simulation and analysis of neural systems, it is essential to have efficient methods for generating artificial spike trains with specified correlation structure. Here we show how correlated binary spike trains can be simulated by means of a latent multivariate gaussian model. Sampling from the model is computationally very efficient and, in particular, feasible even for large populations of neurons. The entropy of the model is close to the theoretical maximum for a wide range of parameters. In addition, this framework naturally extends to correlations over time and offers an elegant way to model correlated neural spike counts with arbitrary marginal distributions
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
- …
