# Simultaneously Learning Architectures and Features of Deep Neural Networks

## TL;DR

This paper introduces a method that jointly optimizes neural network architectures and features through a novel pruning loss and diversity regularization, leading to more efficient models across various tasks.

## Contribution

It presents a new approach for simultaneous architecture and feature learning, improving model compression and accuracy trade-offs.

## Key findings

- Outperforms existing methods in model size and accuracy
- Effective across image classification, compression, and audio tasks
- Enhances model efficiency without sacrificing performance

## Abstract

This paper presents a novel method which simultaneously learns the number of filters and network features repeatedly over multiple epochs. We propose a novel pruning loss to explicitly enforces the optimizer to focus on promising candidate filters while suppressing contributions of less relevant ones. In the meanwhile, we further propose to enforce the diversities between filters and this diversity-based regularization term improves the trade-off between model sizes and accuracies. It turns out the interplay between architecture and feature optimizations improves the final compressed models, and the proposed method is compared favorably to existing methods, in terms of both models sizes and accuracies for a wide range of applications including image classification, image compression and audio classification.