Sort by: Year Popularity Relevance

Testing Conditional Independence in Supervised Learning Algorithms

,  - 2019

We propose a general test of conditional independence. The conditional predictive impact (CPI) is a provably consistent and unbiased estimator of one or several features' association with a given outcome, conditional on a (potentially empty) reduced feature set. Building on the knockoff framework of Cand\`es et al. (2018), we develop a novel test...


REPAIR: Removing Representation Bias by Dataset Resampling

,  - 2019

Modern machine learning datasets can have biases for certain representations that are leveraged by algorithms to achieve high performance without learning to solve the underlying task. This problem is referred to as "representation bias". The question of how to reduce the representation biases of a dataset is investigated and a new dataset REPres...


Locations in the Neocortex: A Theory of Sensorimotor Object Recognition Using Cortical Grid Cells

, , ,  - 2019

The neocortex is capable of anticipating the sensory results of movement but the neural mechanisms are poorly understood. In the entorhinal cortex, grid cells represent the location of an animal in its environment, and this location is updated through movement and path integration. In this paper, we propose that sensory neocortex incorporates movem...


Multi-class Classification without Multi-class Labels

, , , ,  - 2019

This work presents a new strategy for multi-class classification that requires no class-specific labels, but instead leverages pairwise similarity between examples, which is a weaker form of annotation. The proposed method, meta classification learning, optimizes a binary classifier for pairwise similarity prediction and through this process lear...


Learning with Fenchel-Young Losses

, ,  - 2019

Over the past decades, numerous loss functions have been been proposed for a variety of supervised learning tasks, including regression, classification, ranking, and more generally structured prediction. Understanding the core principles and theoretical properties underpinning these losses is key to choose the right loss for the right problem, as...


Bengali Handwritten Character Classification using Transfer Learning on Deep Convolutional Neural Network

, , , ,  - 2019

In this paper, we propose a solution which uses state-of-the-art techniques in Deep Learning to tackle the problem of Bengali Handwritten Character Recognition ( HCR ). Our method uses lesser iterations to train than most other comparable methods. We employ Transfer Learning on ResNet 50, a state-of-the-art deep Convolutional Neural Network Model...


Spatiotemporal CNN for Video Object Segmentation

, , , ,  - 2019

In this paper, we present a unified, end-to-end trainable spatiotemporal CNN model for VOS, which consists of two branches, i.e., the temporal coherence branch and the spatial segmentation branch. Specifically, the temporal coherence branch pretrained in an adversarial fashion from unlabeled video data, is designed to capture the dynamic appearan...


Audio Denoising with Deep Network Priors

,  - 2019

We present a method for audio denoising that combines processing done in both the time domain and the time-frequency domain. Given a noisy audio clip, the method trains a deep neural network to fit this signal. Since the fitting is only partly successful and is able to better capture the underlying clean signal than the noise, the output of the n...


FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network

, , , , ,  - 2019

This paper develops the FastRNN and FastGRNN algorithms to address the twin RNN limitations of inaccurate training and inefficient prediction. Previous approaches have improved accuracy at the expense of prediction costs making them infeasible for resource-constrained and real-time applications. Unitary RNNs have increased accuracy somewhat by re...


LanczosNet: Multi-Scale Deep Graph Convolutional Networks

, , ,  - 2019

We propose the Lanczos network (LanczosNet), which uses the Lanczos algorithm to construct low rank approximations of the graph Laplacian for graph convolution. Relying on the tridiagonal decomposition of the Lanczos algorithm, we not only efficiently exploit multi-scale information via fast approximated computation of matrix power but also desig...