Search Results for author:
Found 12 papers, 2 papers with code
MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of Behavior
We introduce MABe22, a large-scale, multi-agent video and trajectory benchmark to assess the quality of learned behavior representations.
Evaluation metrics for behaviour modeling
A primary difficulty with unsupervised discovery of structure in large data sets is a lack of quantitative evaluation criteria.
Are skip connections necessary for biologically plausible learning rules?
Backpropagation is the workhorse of deep learning, however, several other biologically-motivated learning rules have been introduced, such as random feedback alignment and difference target propagation.
Detecting the Starting Frame of Actions in Video
In this work, we address the problem of precisely localizing key frames of an action, for example, the precise time that a pitcher releases a baseball, or the precise time that a crowd begins to applaud.
Importance Weighted Adversarial Variational Autoencoders for Spike Inference from Calcium Imaging Data
The Importance Weighted Auto Encoder (IWAE) objective has been shown to improve the training of generative models over the standard Variational Auto Encoder (VAE) objective.
Stochastic Neighbor Embedding under f-divergences
A common concern with $t$-SNE criterion is that it is optimized using gradient descent, and can become stuck in poor local minima.
Quantitatively Evaluating GANs With Divergences Proposed for Training
Generative adversarial networks (GANs) have been extremely effective in approximating complex distributions of high-dimensional, input data samples, and substantial progress has been made in understanding and improving GAN performance in terms of both theory and application.
Network-size independent covering number bounds for deep networks
We give a covering number bound for deep learning networks that is independent of the size of the network.
An empirical analysis of the optimization of deep network loss surfaces
The success of deep neural networks hinges on our ability to accurately and efficiently optimize high-dimensional, non-convex functions.
Learning recurrent representations for hierarchical behavior modeling
We propose a framework for detecting action patterns from motion sequences and modeling the sensory-motor relationship of animals, using a generative recurrent neural network.
Understanding Classifier Errors by Examining Influential Neighbors
As computing the influence of each training example is computationally impractical, we propose a novel distance metric to approximate influence for boosting classifiers that is fast enough to be used interactively.
Sample complexity of learning Mahalanobis distance metrics
Metric learning seeks a transformation of the feature space that enhances prediction quality for the given task at hand.
