Search Results for author:
Found 6 papers, 3 papers with code
Labels, Information, and Computation: Efficient Learning Using Sufficient Labels
We call this statistic "sufficiently-labeled data" and prove its sufficiency and efficiency for finding the optimal hidden representations, on which competent classifier heads can be trained using as few as a single randomly-chosen fully-labeled example per class.
Training Deep Architectures Without End-to-End Backpropagation: A Survey on the Provably Optimal Methods
This tutorial paper surveys provably optimal alternatives to end-to-end backpropagation (E2EBP) -- the de facto standard for training deep architectures.
JPD-SE: High-Level Semantics for Joint Perception-Distortion Enhancement in Image Compression
Moreover, they focus mostly on rate-distortion and tend to underperform in perception quality especially in low bitrate regime, and often disregard the performance of downstream computer vision algorithms, which is a fast-growing consumer group of compressed images in addition to human viewers.
Modularizing Deep Learning via Pairwise Learning With Kernels
By redefining the conventional notions of layers, we present an alternative view on finitely wide, fully trainable deep neural networks as stacked linear models in feature spaces, leading to a kernel machine interpretation.
Learning Backpropagation-Free Deep Architectures with Kernels
Moreover, unlike backpropagation, which turns models into black boxes, the optimal hidden representation enjoys an intuitive geometric interpretation, making the dynamics of learning in a deep kernel network simple to understand.
On Kernel Method-Based Connectionist Models and Supervised Deep Learning Without Backpropagation
With this method, we obtain a counterpart of any given NN that is powered by kernel machines instead of neurons.
