GP-CNAS uses genetic programming to automatically design CNN architectures.
problem Designing optimal CNN architectures is laborious and error-prone.
method GP-CNAS uses a tree-based representation of CNNs and dynamic crossover operators to search for optimal architectures.
result GP-CNAS finds optimal CNN architectures with balanced depth and width in limited trials.
Automatically designs CNN architectures for medical image segmentation.
problem Manual design of deep network architectures is time-consuming and resource-intensive.
method Policy gradient reinforcement learning with dice index reward function.
result Efficacy demonstrated with low computational cost compared to state-of-the-art networks.
Optimizes CNN architectures by analyzing receptive fields without training.
problem CNNs often have too many layers, making them resource-intensive and less effective.
method Layer-wise analysis of receptive fields to identify unproductive layers.
result Identifies and removes unproductive layers, improving CNN performance and efficiency.
New ShuffleNASNets improve efficiency and speed of CNN models.
problem Complexity and inefficiency of search-based neural architecture designs.
method Adopted and enhanced Efficient Neural Architecture Search (ENAS) with ShuffleNet V2 principles.
result Achieved significantly less complex, faster, and more efficient CNN models.
New CNN layer selects important channels to improve model capacity.
problem Improving model capacity under resource constraints.
method Selective allocation of channels in convolutional layers.
result New layer allows new optima that generalize better.
GrateTile optimizes CNN feature map storage for efficient data access.
problem Efficient storage and access of sparse CNN feature maps.
method Divides feature maps into uneven-sized subtensors, compresses and stores them in a compressed yet accessible format.
result Average 55% DRAM bandwidth reduction with minimal indexing overhead.
S3NAS finds high-accuracy CNN architectures for NPUs in 3 hours.
problem Finding optimal CNN architectures for NPUs with high accuracy and low latency.
method Supernet design, Single-Path NAS, scaling, analytical latency estimation.
result 82.72% top-1 accuracy on ImageNet with 11.66 ms latency.
Designs a new generative model for images using CNNs and improves generalization and performance.
problem Improving image generation and generalization in CNNs.
method Deconvolutional Generative Model (DGM) using a conjugate prior and Rendering Path Normalization (RPN).
result Improves generalization and performance in semi-supervised and supervised learning tasks.
Morph accelerates 3D CNNs for video recognition, reducing energy consumption and improving performance.
problem Efficiently accelerating 3D CNNs for video recognition is challenging due to their large memory footprint and higher dimensionality.
method Designing a flexible accelerator called Morph that adapts to different spatial and temporal tiling strategies, and codesigning a software infrastructure to control the hardware.
result Morph achieves up to 3.4x reduction in energy consumption and up to 5.1x improvement in performance/watt compared to a baseline 3D CNN accelerator.
NASirt automates CNN architecture design for spectral data.
problem Designing optimal neural architectures for complex data.
method Neural Architecture Search (NAS) with Item Response Theory (IRT) for instance-level complexity.
result NASirt achieves high accuracy (97.40%) on spectral datasets.
Boosting CNNs with dynamic feature selection and boosting weights improves accuracy and efficiency.
problem Expensive training of deep CNNs and manual architecture design.
method Dynamic feature selection, importance sampling, and boosting weights integrated into network training.
result Boosted CNN variants consistently outperform conventional CNNs in accuracy and training speed.
This paper introduces a way to learn cross-modal convolutional neural network (X-CNN) architectures from a base convolutional network (CNN) and the training data to reduce the design cost and enable applying cross-modal networks in sparse data environments. Two approaches for building X-CNNs are presented. The base app…
A hybrid CNN with shared parameters learns to incorporate recurrent structures.
problem Designing efficient recurrent neural networks.
method Parameter sharing scheme combining CNN and recurrent layers.
result Substantial parameter savings with competitive accuracy.
New approach designs optimal structures using GANs and CNNs.
problem Topology design optimization requires many iterations and is impractical for real-world applications.
method Integrates Generative Adversarial Networks (GANs) and convolutional neural networks for topology design.
result Optimal structures generated effectively and rapidly.
New method reduces mobile device energy for image classification.
problem High energy consumption of CNNs on mobile devices.
method Global optimization of CNN architectures with Bayesian optimization.
result Reduces energy consumption by up to 6x compared to blackbox CNNs.
Study improves CNNs for audio scene classification by restricting receptive fields and adding frequency awareness.
problem Improving CNNs for robust acoustic scene classification.
method Investigated different receptive field configurations for various CNN architectures and introduced Frequency Aware CNNs.
result Several well-performing submissions to DCASE 2019 Challenge were achieved.
This study examines how model architecture affects deep learning model privacy.
problem Privacy concerns in deep learning models due to potential leakage of sensitive information.
method Investigation of CNNs and Transformers, focusing on activation layers, stem layers, LN layers, and attention modules.
result Transformers generally exhibit higher vulnerability to privacy attacks than CNNs.
Deep CapsNet improves sign language recognition from wearable IMUs.
problem Continuous recognition of sign language from wearable devices.
method Custom CapsNet architecture using deep capsule networks and game theory.
result Improved accuracy of 94% and 92.50% for 3 and 5 routings respectively, compared to 87.99% for CNN.
New insights suggest larger early layers improve CNN performance.
problem Common assumption of monotonously increasing feature counts in CNNs is challenged.
method Used a skew normal distribution to investigate feature amounts in CNN layers.
result Architectures favoring larger early layers yield better accuracy.
AOFP prunes CNN filters faster and more accurately.
problem Finding optimal CNN width and pruning filters efficiently.
method Binary search, random masking, multi-path framework.
result AOFP achieves faster pruning with minimal accuracy loss.
Large receptive field CNNs improve distant speech recognition.
problem Degrading performance of ASR systems in noisy environments.
method Investigated large receptive field CNN variants including recursive, dilated, and hourglass networks.
result Stacked hourglass networks show significant improvements in distant speech recognition.
This work automates CNN model compression for mobile devices.
problem Deploying trained CNNs to mobile devices requires balancing speed, memory, and accuracy.
method Reinforcement learning with architecture search and knowledge distillation.
result An automated model compression algorithm improves the trade-off between speed, memory, and accuracy.
Achieving superhuman playing level by AlphaGo corroborated the capabilities of convolutional neural architectures (CNNs) for capturing complex spatial patterns. This result was to a great extent due to several analogies between Go board states and 2D images CNNs have been designed for, in particular translational invar…
Early diagnosis of interstitial lung diseases is crucial for their treatment, but even experienced physicians find it difficult, as their clinical manifestations are similar. In order to assist with the diagnosis, computer-aided diagnosis (CAD) systems have been developed. These commonly rely on a fixed scale classifie…
SGAS improves neural architecture search by choosing and pruning operations greedily.
problem NAS often fails to generalize in final evaluation.
method Divides search into sub-problems and chooses/prunes candidate operations greedily.
result SGAS finds state-of-the-art architectures with minimal computational cost.
Winograd convolutions are used to improve quantized neural networks.
problem Improving quantized neural networks using Winograd convolutions.
method Proposed a Winograd-aware formulation of convolution layers to expose numerical inaccuracies to learning.
result Up to 10% higher classification accuracy on CIFAR-10 with Winograd-aware layers.
Novel CNN array for sign language recognition using wearable IMUs.
problem Efficiently recognizing sign language from wearable IMU signals.
method Two-dimensional Convolutional Neural Network array architecture for Indian sign language recognition.
result Peak classification accuracies of 94.20% for general sentences and 95.00% for interrogative sentences achieved.
Proposes continuous convolution layers for flexible feature map resizing.
problem Fixed stride limitations in discrete convolution layers.
method Introduces Continuous Convolution (CC) layers that use learned continuous functions.
result Dynamic and consistent resizing of feature maps at any scale, non-integer and axis-dependent.
In recent years, state-of-the-art methods in computer vision have utilized increasingly deep convolutional neural network architectures (CNNs), with some of the most successful models employing hundreds or even thousands of layers. A variety of pathologies such as vanishing/exploding gradients make training such deep n…
Alternative optimizer outperforms gradient descent in weakly-supervised CNN segmentation.
problem Training deep neural networks with complex loss functions.
method Demonstrated an alternative optimizer (ADM) outperforming gradient descent.
result Gradient descent performs poorly with certain loss functions, while an alternative optimizer achieves state-of-the-art results.
Pruning FCNs reveals sub-networks that match CNNs' performance.
problem Understanding the inductive bias of pruning in neural networks.
method Iterative magnitude pruning of a simple FCN followed by analysis of the resulting architecture.
result Pruned FCNs exhibit key features of CNNs, suggesting new architectural biases.
This paper analyzes CNNs for malware detection in cloud IaaS.
problem Malware vulnerability in cloud IaaS environments.
method Analysis of Convolutional Neural Networks (CNNs) for online malware detection using process-level performance metrics.
result State-of-the-art DenseNets and ResNets effectively detect malware in online cloud systems.
Net2Vis automates CNN visualization for publications.
problem Lack of consistent visual representations in deep learning papers.
method Proposes a visual grammar and automated system for generating publication-ready CNN visualizations.
result Reduces time and ambiguity in generating network visualizations.
Computer vision performances have been significantly improved in recent years by Convolutional Neural Networks(CNN). Currently, applications using CNN algorithms are deployed mainly on general purpose hardwares, such as CPUs, GPUs or FPGAs. However, power consumption, speed, accuracy, memory footprint, and die size sho…
Two architectures that generalize convolutional neural networks (CNNs) for the processing of signals supported on graphs are introduced. We start with the selection graph neural network (GNN), which replaces linear time invariant filters with linear shift invariant graph filters to generate convolutional features and r…
DNArch learns CNN architectures by backpropagation.
problem Discovering optimal CNN architectures.
method Differentiable Neural Architectures (DNArch) learns CNN architectures by backpropagation, controlling kernel sizes, channels, downsampling positions, and depth.
result DNArch finds performant CNN architectures across various tasks.
In this paper we propose cross-modal convolutional neural networks (X-CNNs), a novel biologically inspired type of CNN architectures, treating gradient descent-specialised CNNs as individual units of processing in a larger-scale network topology, while allowing for unconstrained information flow and/or weight sharing b…
Enhances CNN feature extractors' separation capacity analysis.
problem Understanding the separation capacity of CNNs.
method Extending Cover's function-counting theory, analyzing scattering networks.
result Identifies factors affecting scattering networks' separation capacity.
New CNN initialization scheme derived from modern architectures.
problem Stability of CNN model parameters initialization.
method Derived new initialization scheme from modern CNN architectures.
result New initialization method outperforms de facto standard schemes.
Neural networks have recently had a lot of success for many tasks. However, neural network architectures that perform well are still typically designed manually by experts in a cumbersome trial-and-error process. We propose a new method to automatically search for well-performing CNN architectures based on a simple hil…
ESM-CNN uses error feedback to build a random CNN for time series forecasting.
problem Improving time series forecasting accuracy with CNNs.
method Incrementally adding random filters and neurons to adaptively construct a CNN.
result ESM-CNN outperforms state-of-the-art models in prediction accuracy and efficiency.
CNN-F uses generative feedback to improve neural networks' robustness to perturbations.
problem Neural networks' vulnerability to input perturbations like noise and attacks.
method Enforces self-consistency in neural networks by incorporating generative recurrent feedback.
result CNN-F shows significantly improved adversarial robustness compared to conventional CNNs.
Efficient CNN for VQA achieves similar performance to standard models.
problem Computational intensity of standard VQA models.
method Proposes a sparsely activated CNN architecture.
result Sparsely activated CNN achieves comparable performance.
Neuroscientists classify neurons into different types that perform similar computations at different locations in the visual field. Traditional methods for neural system identification do not capitalize on this separation of 'what' and 'where'. Learning deep convolutional feature spaces that are shared among many neuro…
This work ranks CNN filters based on their importance.
problem Unclear role of CNN neurons in producing output.
method Two methods: Shapley value game theory and Importance switch variational inference.
result Filters with higher importance are more crucial for output.
Automates resource-efficient CNN design for IoT.
problem Designing custom CNNs for IoT applications is impractical and resource-intensive.
method Automated synthesis of resource scalable CNNs from an existing optimized baseline CNN.
result Synthesized CNNs are resource-efficient and competitive in accuracy.
In this work, we investigate the value of employing deep learning for the task of wireless signal modulation recognition. Recently in [1], a framework has been introduced by generating a dataset using GNU radio that mimics the imperfections in a real wireless channel, and uses 10 different modulation types. Further, a …
Identifying the distribution of users' transportation modes is an essential part of travel demand analysis and transportation planning. With the advent of ubiquitous GPS-enabled devices (e.g., a smartphone), a cost-effective approach for inferring commuters' mobility mode(s) is to leverage their GPS trajectories. A maj…