Related papers: DoReFa-Net: Training Low Bitwidth Convolutional Ne…
Research has shown that deep neural networks contain significant redundancy, and that high classification accuracies can be achieved even when weights and activations are quantised down to binary values. Network binarisation on FPGAs…
In this paper, the multi-task learning of lightweight convolutional neural networks is studied for face identification and classification of facial attributes (age, gender, ethnicity) trained on cropped faces without margins. The necessity…
The state-of-the-art hardware platforms for training Deep Neural Networks (DNNs) are moving from traditional single precision (32-bit) computations towards 16 bits of precision -- in large part due to the high energy efficiency and smaller…
We propose a Coefficient-to-Basis Network (C2BNet), a novel framework for solving inverse problems within the operator learning paradigm. C2BNet efficiently adapts to different discretizations through fine-tuning, using a pre-trained model…
The increasing complexity of deep learning architectures is resulting in training time requiring weeks or even months. This slow training is due in part to vanishing gradients, in which the gradients used by back-propagation are extremely…
Personalizing visual generative models to meet specific user needs has gained increasing attention, yet current methods like Low-Rank Adaptation (LoRA) remain impractical due to their demand for task-specific data and lengthy optimization.…
Binary neural networks (BNNs) have 1-bit weights and activations. Such networks are well suited for FPGAs, as their dominant computations are bitwise arithmetic and the memory requirement is also significantly reduced. However, compared to…
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…
Pruning neural networks has regained interest in recent years as a means to compress state-of-the-art deep neural networks and enable their deployment on resource-constrained devices. In this paper, we propose a robust compressive learning…
Deep neural networks have rapidly become the mainstream method for face recognition (FR). However, this limits the deployment of such models that contain an extremely large number of parameters to embedded and low-end devices. In this work,…
Deep learning network training is usually computationally expensive and intuitively complex. We present a novel network architecture for custom training and weight evaluations. We reformulate the layers as ResNet-similar blocks with certain…
Prior work introduced a gradient descent trained expert system that conceptually combines the learning capabilities of neural networks with the understandability and defensible logic of an expert system. This system was shown to be able to…
We study the training of deep neural networks by gradient descent where floating-point arithmetic is used to compute the gradients. In this framework and under realistic assumptions, we demonstrate that it is highly unlikely to find ReLU…
There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the…
Medical imaging deep learning models are often large and complex, requiring specialized hardware to train and evaluate these models. To address such issues, we propose the PocketNet paradigm to reduce the size of deep learning models by…
Network quantization has rapidly become one of the most widely used methods to compress and accelerate deep neural networks. Recent efforts propose to quantize weights and activations from different layers with different precision to…
Existing parameter-efficient fine-tuning (PEFT) methods primarily adapt weight matrices while keeping activation functions fixed. We introduce \textbf{NoRA}, the first PEFT framework that directly adapts nonlinear activation functions in…
A recent line of research has shown that gradient-based algorithms with random initialization can converge to the global minima of the training loss for over-parameterized (i.e., sufficiently wide) deep neural networks. However, the…
Parameter-efficient fine-tuning (PEFT) methods reduce the computational costs of updating deep learning models by minimizing the number of additional parameters used to adapt a model to a down- stream task. While extensively researched in…
To solve high-dimensional parameter-dependent partial differential equations (pPDEs), a neural network architecture is presented. It is constructed to map parameters of the model data to corresponding finite element solutions. To improve…