Related papers: Machine Learning with Clos Networks
Recurrent Neural Networks (RNNs) produce state-of-art performance on many machine learning tasks but their demand on resources in terms of memory and computational power are often high. Therefore, there is a great interest in optimizing the…
Deep networks for visual recognition are known to leverage "easy to recognise" portions of objects such as faces and distinctive texture patterns. The lack of a holistic understanding of objects may increase fragility and overfitting. In…
We present a novel optimization strategy for training neural networks which we call "BitNet". The parameters of neural networks are usually unconstrained and have a dynamic range dispersed over all real values. Our key idea is to limit the…
In this work we establish the relation between optimal control and training deep Convolution Neural Networks (CNNs). We show that the forward propagation in CNNs can be interpreted as a time-dependent nonlinear differential equation and…
Previous works proved that the combination of the linear neuron network with nonlinear activation functions (e.g. ReLu) can achieve nonlinear function approximation. However, simply widening or deepening the network structure will introduce…
We show how fitting sparse linear models over learned deep feature representations can lead to more debuggable neural networks. These networks remain highly accurate while also being more amenable to human interpretation, as we demonstrate…
The goal of model compression is to reduce the size of a large neural network while retaining a comparable performance. As a result, computation and memory costs in resource-limited applications may be significantly reduced by dropping…
We present an analysis of different techniques for selecting the connection be- tween layers of deep neural networks. Traditional deep neural networks use ran- dom connection tables between layers to keep the number of connections small and…
Neural Networks are function approximators that have achieved state-of-the-art accuracy in numerous machine learning tasks. In spite of their great success in terms of accuracy, their large training time makes it difficult to use them for…
Various natural language processing tasks are structured prediction problems where outputs are constructed with multiple interdependent decisions. Past work has shown that domain knowledge, framed as constraints over the output space, can…
In this paper, we will describe a network architecture that demonstrates high performance on various sizes of datasets. To do this, we will perform an architecture search by dividing the fully connected layer into three levels in the…
Network pruning reduces the size of neural networks by removing (pruning) neurons such that the performance drop is minimal. Traditional pruning approaches focus on designing metrics to quantify the usefulness of a neuron which is often…
Model pruning can enable the deployment of neural networks in environments with resource constraints. While pruning may have a small effect on the overall performance of the model, it can exacerbate existing biases into the model such that…
Network-based transfer learning allows the reuse of deep learning features with limited data, but the resulting models can be unnecessarily large. Although network pruning can improve inference efficiency, existing algorithms usually…
In this paper, we investigate the effectiveness of deep learning techniques for lung nodule classification in computed tomography scans. Using less than 10,000 training examples, our deep networks perform two times better than a standard…
This paper presents an efficient technique to prune deep and/or wide convolutional neural network models by eliminating redundant features (or filters). Previous studies have shown that over-sized deep neural network models tend to produce…
We train neural networks to optimize a Minimum Description Length score, i.e., to balance between the complexity of the network and its accuracy at a task. We show that networks optimizing this objective function master tasks involving…
Giving provable guarantees for learning neural networks is a core challenge of machine learning theory. Most prior work gives parameter recovery guarantees for one hidden layer networks, however, the networks used in practice have multiple…
We present a novel modular object detection convolutional neural network that significantly improves the accuracy of object detection. The network consists of two stages in a hierarchical structure. The first stage is a network that detects…
A low precision deep neural network training technique for producing sparse, ternary neural networks is presented. The technique incorporates hard- ware implementation costs during training to achieve significant model compression for…