Related papers: OCCAM: Optimal Data Reuse for Convolutional Neural…

Scaling CNN training is necessary to keep up with growing datasets and reduce training time. We also see an emerging need to handle datasets with very large samples, where memory requirements for training are large. Existing training…

The Convolutional Neural Networks (CNNs), in domains like computer vision, mostly reduced the need for handcrafted features due to its ability to learn the problem-specific features from the raw input data. However, the selection of…

Orthogonal convolutional layers are valuable components in multiple areas of machine learning, such as adversarial robustness, normalizing flows, GANs, and Lipschitz-constrained models. Their ability to preserve norms and ensure stable…

Convolutional Neural Networks (CNNs) are powerful models that achieve impressive results for image classification. In addition, pre-trained CNNs are also useful for other computer vision tasks as generic feature extractors. This paper aims…

Binary Convolutional Neural Networks (CNNs) can significantly reduce the number of arithmetic operations and the size of memory storage, which makes the deployment of CNNs on mobile or embedded systems more promising. However, the accuracy…

Herein, a bit-wise Convolutional Neural Network (CNN) in-memory accelerator is implemented using Spin-Orbit Torque Magnetic Random Access Memory (SOT-MRAM) computational sub-arrays. It utilizes a novel AND-Accumulation method capable of…

Predicting attributes from face images in the wild is a challenging computer vision problem. To automatically describe face attributes from face containing images, traditionally one needs to cascade three technical blocks --- face…

The computational demands of computer vision tasks based on state-of-the-art Convolutional Neural Network (CNN) image classification far exceed the energy budgets of mobile devices. This paper proposes FixyNN, which consists of a…

Applying convolutional neural networks to large images is computationally expensive because the amount of computation scales linearly with the number of image pixels. We present a novel recurrent neural network model that is capable of…

Convolutional Recurrent Neural Networks (CRNNs) excel at scene text recognition. Unfortunately, they are likely to suffer from vanishing/exploding gradient problems when processing long text images, which are commonly found in scanned…

Spiking neural networks (SNNs) have become an interesting alternative to conventional artificial neural networks (ANN) thanks to their temporal processing capabilities and energy efficient implementations in neuromorphic hardware. However…

Facial expression recognition is a major problem in the domain of artificial intelligence. One of the best ways to solve this problem is the use of convolutional neural networks (CNNs). However, a large amount of data is required to train…

We propose a novel deep convolutional neural network (CNN) based multi-task learning approach for open-set visual recognition. We combine a classifier network and a decoder network with a shared feature extractor network within a multi-task…

Recent advances in integrated photonics enable the implementation of reconfigurable, high-bandwidth, and low energy-per-bit interconnects in next-generation data centers. We propose and evaluate an Optically Connected Memory (OCM)…

Many state-of-the-art computer vision algorithms use large scale convolutional neural networks (CNNs) as basic building blocks. These CNNs are known for their huge number of parameters, high redundancy in weights, and tremendous computing…

As the demand for efficient, low-power computing in embedded and edge devices grows, traditional computing methods are becoming less effective for handling complex tasks. Stochastic computing (SC) offers a promising alternative by…

Filters are the essential elements in convolutional neural networks (CNNs). Filters are corresponded to the feature maps and form the main part of the computational and memory requirement for the CNN processing. In filter pruning methods, a…

Compressive sensing (CS), aiming to reconstruct an image/signal from a small set of random measurements has attracted considerable attentions in recent years. Due to the high dimensionality of images, previous CS methods mainly work on…

ML and HPC applications increasingly combine dense and sparse memory access computations to maximize storage efficiency. However, existing CPUs and GPUs struggle to flexibly handle these heterogeneous workloads with consistently high…

With the increasing reliance of users on smart devices, bringing essential computation at the edge has become a crucial requirement for any type of business. Many such computations utilize Convolution Neural Networks (CNNs) to perform AI…