Search Results for author:
Found 16 papers, 5 papers with code
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models.
Large image datasets: A pyrrhic win for computer vision?
In this paper we investigate problematic practices and consequences of large scale vision datasets.
Deep Connectomics Networks: Neural Network Architectures Inspired by Neuronal Networks
The interplay between inter-neuronal network topology and cognition has been studied deeply by connectomics researchers and network scientists, which is crucial towards understanding the remarkable efficacy of biological neural networks.
Model Weight Theft With Just Noise Inputs: The Curious Case of the Petulant Attacker
Bernoulli noise inputs.
Grassmannian Packings in Neural Networks: Learning with Maximal Subspace Packings for Diversity and Anti-Sparsity
Kernel sparsity ("dying ReLUs") and lack of diversity are commonly observed in CNN kernels, which decreases model capacity.
Kannada-MNIST: A new handwritten digits dataset for the Kannada language
In addition to this dataset, we disseminate an additional real world handwritten dataset (with $10k$ images), which we term as the Dig-MNIST dataset that can serve as an out-of-domain test dataset.
Understanding Adversarial Robustness Through Loss Landscape Geometries
In this paper, we harness the state-of-the-art "filter normalization" technique of loss-surface visualization to qualitatively understand the consequences of using adversarial training data augmentation as the explicit regularization technique of choice.
Covering up bias in CelebA-like datasets with Markov blankets: A post-hoc cure for attribute prior avoidance
Attribute prior avoidance entails subconscious or willful non-modeling of (meta)attributes that datasets are oft born with, such as the 40 semantic facial attributes associated with the CelebA and CelebA-HQ datasets.
Grassmannian initialization: Neural network initialization using sub-space packing
We recently observed that convolutional filters initialized farthest apart from each other using offthe- shelf pre-computed Grassmannian subspace packing codebooks performed surprisingly well across many datasets.
Deep connectomics networks: Results from neural network architectures inspired from network neuroscience
Using the teachings from network neuroscience and connectomics, we show improvements over the ResNet architecture, we show a possible connection between early training and the spectral properties of the network, and we show the trainability of a DNN based on the neuronal network of C. Elegans.
Do deep neural networks learn shallow learnable examples first?
In this paper, we empirically investigate the training journey of deep neural networks relative to fully trained shallow machine learning models.
Fonts-2-Handwriting: A Seed-Augment-Train framework for universal digit classification
In this paper, we propose a Seed-Augment-Train/Transfer (SAT) framework that contains a synthetic seed image dataset generation procedure for languages with different numeral systems using freely available open font file datasets.
A Seed-Augment-Train Framework for Universal Digit Classification
In this paper, we propose a Seed-Augment-Train/Transfer (SAT) framework that contains a synthetic seed image dataset generation procedure for languages with different numeral systems using freely available open font file datasets.
On Lyapunov exponents and adversarial perturbation
In this paper, we would like to disseminate a serendipitous discovery involving Lyapunov exponents of a 1-D time series and their use in serving as a filtering defense tool against a specific kind of deep adversarial perturbation.
