scholarly journals State-Space Representations of Deep Neural Networks

2019 ◽  
Vol 31 (3) ◽  
pp. 538-554
Author(s):  
Michael Hauser ◽  
Sean Gunn ◽  
Samer Saab ◽  
Asok Ray
Keyword(s):  
Neural Networks ◽  
State Space ◽  
Deep Neural Networks ◽  
The State ◽  
Network Architectures ◽  
Embedding Dimension ◽  
Dynamical Equations ◽  
Closed Form Solutions ◽  
Dense Networks ◽  
Finite Difference Equations

This letter deals with neural networks as dynamical systems governed by finite difference equations. It shows that the introduction of [Formula: see text]-many skip connections into network architectures, such as residual networks and additive dense networks, defines [Formula: see text]th order dynamical equations on the layer-wise transformations. Closed-form solutions for the state-space representations of general [Formula: see text]th order additive dense networks, where the concatenation operation is replaced by addition, as well as [Formula: see text]th order smooth networks, are found. The developed provision endows deep neural networks with an algebraic structure. Furthermore, it is shown that imposing [Formula: see text]th order smoothness on network architectures with [Formula: see text]-many nodes per layer increases the state-space dimension by a multiple of [Formula: see text], and so the effective embedding dimension of the data manifold by the neural network is [Formula: see text]-many dimensions. It follows that network architectures of these types reduce the number of parameters needed to maintain the same embedding dimension by a factor of [Formula: see text] when compared to an equivalent first-order, residual network. Numerical simulations and experiments on CIFAR10, SVHN, and MNIST have been conducted to help understand the developed theory and efficacy of the proposed concepts.

Location- and Person-Independent Activity Recognition with WiFi, Deep Neural Networks, and Reinforcement Learning

2021 ◽  
Vol 2 (1) ◽  
pp. 1-25
Author(s):  
Yongsen Ma ◽  
Sheheryar Arshad ◽  
Swetha Muniraju ◽  
Eric Torkildson ◽  
Enrico Rantala ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Reinforcement Learning ◽  
Activity Recognition ◽  
Deep Neural Networks ◽  
State Machine ◽  
Recognition Algorithm ◽  
The State ◽  
Neural Architecture ◽  
Learning Agent

In recent years, Channel State Information (CSI) measured by WiFi is widely used for human activity recognition. In this article, we propose a deep learning design for location- and person-independent activity recognition with WiFi. The proposed design consists of three Deep Neural Networks (DNNs): a 2D Convolutional Neural Network (CNN) as the recognition algorithm, a 1D CNN as the state machine, and a reinforcement learning agent for neural architecture search. The recognition algorithm learns location- and person-independent features from different perspectives of CSI data. The state machine learns temporal dependency information from history classification results. The reinforcement learning agent optimizes the neural architecture of the recognition algorithm using a Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM). The proposed design is evaluated in a lab environment with different WiFi device locations, antenna orientations, sitting/standing/walking locations/orientations, and multiple persons. The proposed design has 97% average accuracy when testing devices and persons are not seen during training. The proposed design is also evaluated by two public datasets with accuracy of 80% and 83%. The proposed design needs very little human efforts for ground truth labeling, feature engineering, signal processing, and tuning of learning parameters and hyperparameters.

scholarly journals Modified Deep Neural Networks for Dog Breeds Identification

2018 ◽  
Author(s):  
Aydin Ayanzadeh ◽  
Sahand Vahidnia
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
The State ◽  
Fine Tuning ◽  
Test Accuracy ◽  
Data Sets ◽  
Data Set

In this paper, we leverage state of the art models on Imagenet data-sets. We use the pre-trained model and learned weighs to extract the feature from the Dog breeds identification data-set. Afterwards, we applied fine-tuning and dataaugmentation to increase the performance of our test accuracy in classification of dog breeds datasets. The performance of the proposed approaches are compared with the state of the art models of Image-Net datasets such as ResNet-50, DenseNet-121, DenseNet-169 and GoogleNet. we achieved 89.66% , 85.37% 84.01% and 82.08% test accuracy respectively which shows thesuperior performance of proposed method to the previous works on Stanford dog breeds datasets.

scholarly journals Interpolation Consistency Training for Semi-supervised Learning

2019 ◽  
Author(s):  
Vikas Verma ◽  
Alex Lamb ◽  
Juho Kannala ◽  
Yoshua Bengio ◽  
David Lopez-Paz
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Supervised Learning ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Data Distribution ◽  
Network Architectures ◽  
Low Density ◽  
Decision Boundary ◽  
Classification Problems

We introduce Interpolation Consistency Training (ICT), a simple and computation efficient algorithm for training Deep Neural Networks in the semi-supervised learning paradigm. ICT encourages the prediction at an interpolation of unlabeled points to be consistent with the interpolation of the predictions at those points. In classification problems, ICT moves the decision boundary to low-density regions of the data distribution. Our experiments show that ICT achieves state-of-the-art performance when applied to standard neural network architectures on the CIFAR-10 and SVHN benchmark dataset.

scholarly journals Evaluating Dropout Placements in Bayesian Regression Resnet

2021 ◽  
Vol 12 (1) ◽  
pp. 61-73
Author(s):  
Lei Shi ◽  
Cosmin Copot ◽  
Steve Vanlanduit
Keyword(s):  
Neural Networks ◽  
Model Uncertainty ◽  
Coverage Probability ◽  
Deep Neural Networks ◽  
Bayesian Regression ◽  
Great Success ◽  
Network Architectures ◽  
Deep Architecture ◽  
Bayesian Approximation ◽  
Interval Coverage

Abstract Deep Neural Networks (DNNs) have shown great success in many fields. Various network architectures have been developed for different applications. Regardless of the complexities of the networks, DNNs do not provide model uncertainty. Bayesian Neural Networks (BNNs), on the other hand, is able to make probabilistic inference. Among various types of BNNs, Dropout as a Bayesian Approximation converts a Neural Network (NN) to a BNN by adding a dropout layer after each weight layer in the NN. This technique provides a simple transformation from a NN to a BNN. However, for DNNs, adding a dropout layer to each weight layer would lead to a strong regularization due to the deep architecture. Previous researches [1, 2, 3] have shown that adding a dropout layer after each weight layer in a DNN is unnecessary. However, how to place dropout layers in a ResNet for regression tasks are less explored. In this work, we perform an empirical study on how different dropout placements would affect the performance of a Bayesian DNN. We use a regression model modified from ResNet as the DNN and place the dropout layers at different places in the regression ResNet. Our experimental results show that it is not necessary to add a dropout layer after every weight layer in the Regression ResNet to let it be able to make Bayesian Inference. Placing Dropout layers between the stacked blocks i.e. Dense+Identity+Identity blocks has the best performance in Predictive Interval Coverage Probability (PICP). Placing a dropout layer after each stacked block has the best performance in Root Mean Square Error (RMSE).

scholarly journals Spoofing Speaker Verification System by Adversarial Examples Leveraging the Generalized Speaker Difference

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Hongwei Luo ◽  
Yijie Shen ◽  
Feng Lin ◽  
Guoai Xu
Keyword(s):  
Neural Networks ◽  
Loss Function ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Speaker Verification ◽  
Signal To Noise Ratio ◽  
The State ◽  
Verification System ◽  
Adversarial Examples ◽  
Human Hearing

Speaker verification system has gained great popularity in recent years, especially with the development of deep neural networks and Internet of Things. However, the security of speaker verification system based on deep neural networks has not been well investigated. In this paper, we propose an attack to spoof the state-of-the-art speaker verification system based on generalized end-to-end (GE2E) loss function for misclassifying illegal users into the authentic user. Specifically, we design a novel loss function to deploy a generator for generating effective adversarial examples with slight perturbation and then spoof the system with these adversarial examples to achieve our goals. The success rate of our attack can reach 82% when cosine similarity is adopted to deploy the deep-learning-based speaker verification system. Beyond that, our experiments also reported the signal-to-noise ratio at 76 dB, which proves that our attack has higher imperceptibility than previous works. In summary, the results show that our attack not only can spoof the state-of-the-art neural-network-based speaker verification system but also more importantly has the ability to hide from human hearing or machine discrimination.

scholarly journals Network Approximation using Tensor Sketching

2018 ◽  
Author(s):  
Shiva Prasad Kasiviswanathan ◽  
Nina Narodytska ◽  
Hongxia Jin
Keyword(s):  
Neural Networks ◽  
Language Processing ◽  
Network Architecture ◽  
Deep Neural Networks ◽  
Network Architectures ◽  
Effective Parameters ◽  
Unified Framework ◽  
Design Changes ◽  
Target Network ◽  
Fully Connected

Deep neural networks are powerful learning models that achieve state-of-the-art performance on many computer vision, speech, and language processing tasks. In this paper, we study a fundamental question that arises when designing deep network architectures: Given a target network architecture can we design a `smaller' network architecture that 'approximates' the operation of the target network? The question is, in part, motivated by the challenge of parameter reduction (compression) in modern deep neural networks, as the ever increasing storage and memory requirements of these networks pose a problem in resource constrained environments.In this work, we focus on deep convolutional neural network architectures, and propose a novel randomized tensor sketching technique that we utilize to develop a unified framework for approximating the operation of both the convolutional and fully connected layers. By applying the sketching technique along different tensor dimensions, we design changes to the convolutional and fully connected layers that substantially reduce the number of effective parameters in a network. We show that the resulting smaller network can be trained directly, and has a classification accuracy that is comparable to the original network.

scholarly journals Design Challenges for Entity Linking

2015 ◽  
Vol 3 ◽  
pp. 315-328 ◽  
Author(s):  
Xiao Ling ◽  
Sameer Singh ◽  
Daniel S. Weld
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
The State ◽  
Data Sets ◽  
Entity Linking ◽  
Joint Inference ◽  
Extensive Evaluation ◽  
Key Aspects ◽  
Design Challenges

Recent research on entity linking (EL) has introduced a plethora of promising techniques, ranging from deep neural networks to joint inference. But despite numerous papers there is surprisingly little understanding of the state of the art in EL. We attack this confusion by analyzing differences between several versions of the EL problem and presenting a simple yet effective, modular, unsupervised system, called Vinculum, for entity linking. We conduct an extensive evaluation on nine data sets, comparing Vinculum with two state-of-the-art systems, and elucidate key aspects of the system that include mention extraction, candidate generation, entity type prediction, entity coreference, and coherence.

scholarly journals An optical neural network using less than 1 photon per multiplication

2022 ◽  
Vol 13 (1) ◽  
Author(s):  
Tianyu Wang ◽  
Shi-Yuan Ma ◽  
Logan G. Wright ◽  
Tatsuhiro Onodera ◽  
Brian C. Richard ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Deep Neural Networks ◽  
Fundamental Principle ◽  
Energy Costs ◽  
Network Architectures ◽  
Optical Neural Networks ◽  
Optical Neural Network ◽  
Handwritten Digit

AbstractDeep learning has become a widespread tool in both science and industry. However, continued progress is hampered by the rapid growth in energy costs of ever-larger deep neural networks. Optical neural networks provide a potential means to solve the energy-cost problem faced by deep learning. Here, we experimentally demonstrate an optical neural network based on optical dot products that achieves 99% accuracy on handwritten-digit classification using ~3.1 detected photons per weight multiplication and ~90% accuracy using ~0.66 photons (~2.5 × 10−19 J of optical energy) per weight multiplication. The fundamental principle enabling our sub-photon-per-multiplication demonstration—noise reduction from the accumulation of scalar multiplications in dot-product sums—is applicable to many different optical-neural-network architectures. Our work shows that optical neural networks can achieve accurate results using extremely low optical energies.

scholarly journals Interaffection of Multiple Datasets with Neural Networks in Speech Emotion Recognition

2020 ◽  
Author(s):  
Ronnypetson Da Silva ◽  
Valter M. Filho ◽  
Mario Souza
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Emotion Recognition ◽  
Deep Neural Networks ◽  
Speech Emotion Recognition ◽  
Network Architectures ◽  
Shared Representations ◽  
Multiple Datasets ◽  
Neural Network Architectures

Many works that apply Deep Neural Networks (DNNs) to Speech Emotion Recognition (SER) use single datasets or train and evaluate the models separately when using multiple datasets. Those datasets are constructed with specific guidelines and the subjective nature of the labels for SER makes it difficult to obtain robust and general models. We investigate how DNNs learn shared representations for different datasets in both multi-task and unified setups. We also analyse how each dataset benefits from others in different combinations of datasets and popular neural network architectures. We show that the longstanding belief of more data resulting in more general models doesn’t always hold for SER, as different dataset and meta-parameter combinations hold the best result for each of the analysed datasets.

Sign in / Sign up

Export Citation Format

Share Document