Effective Building Block Design for Deep Convolutional Neural Networks using Search

01/25/2018
by   Jayanta K. Dutta, et al.
0

Deep learning has shown promising results on many machine learning tasks but DL models are often complex networks with large number of neurons and layers, and recently, complex layer structures known as building blocks. Finding the best deep model requires a combination of finding both the right architecture and the correct set of parameters appropriate for that architecture. In addition, this complexity (in terms of layer types, number of neurons, and number of layers) also present problems with generalization since larger networks are easier to overfit to the data. In this paper, we propose a search framework for finding effective architectural building blocks for convolutional neural networks (CNN). Our approach is much faster at finding models that are close to state-of-the-art in performance. In addition, the models discovered by our approach are also smaller than models discovered by similar techniques. We achieve these twin advantages by designing our search space in such a way that it searches over a reduced set of state-of-the-art building blocks for CNNs including residual block, inception block, inception-residual block, ResNeXt block and many others. We apply this technique to generate models for multiple image datasets and show that these models achieve performance comparable to state-of-the-art (and even surpassing the state-of-the-art in one case). We also show that learned models are transferable between datasets.

READ FULL TEXT
research
01/28/2020

CSNNs: Unsupervised, Backpropagation-free Convolutional Neural Networks for Representation Learning

This work combines Convolutional Neural Networks (CNNs), clustering via ...
research
04/06/2019

Effective and Efficient Dropout for Deep Convolutional Neural Networks

Machine-learning-based data-driven applications have become ubiquitous, ...
research
11/27/2018

Combining Deep Learning and Qualitative Spatial Reasoning to Learn Complex Structures from Sparse Examples with Noise

Many modern machine learning approaches require vast amounts of training...
research
03/06/2020

AutoML-Zero: Evolving Machine Learning Algorithms From Scratch

Machine learning research has advanced in multiple aspects, including mo...
research
08/22/2013

Learning Deep Representation Without Parameter Inference for Nonlinear Dimensionality Reduction

Unsupervised deep learning is one of the most powerful representation le...
research
10/30/2017

CrescendoNet: A Simple Deep Convolutional Neural Network with Ensemble Behavior

We introduce a new deep convolutional neural network, CrescendoNet, by s...
research
08/18/2020

Feature Products Yield Efficient Networks

We introduce Feature-Product networks (FP-nets) as a novel deep-network ...

Please sign up or login with your details

Forgot password? Click here to reset