Related papers: Transferable Learning on Analog Hardware
Thanks to digitization of industrial assets in fleets, the ambitious goal of transferring fault diagnosis models fromone machine to the other has raised great interest. Solving these domain adaptive transfer learning tasks has the potential…
Reconfigurable photonic mesh networks of tunable beamsplitter nodes can linearly transform $N$-dimensional vectors representing input modal amplitudes of light for applications such as energy-efficient machine learning hardware, quantum…
With an ever-growing number of parameters defining increasingly complex networks, Deep Learning has led to several breakthroughs surpassing human performance. As a result, data movement for these millions of model parameters causes a…
In Convolutional Neural Network (CNN) based image processing, most of the studies propose networks that are optimized for a single-level (or a single-objective); thus, they underperform on other levels and must be retrained for delivery of…
Deep neural networks are capable of training fast and generalizing well within many domains. Despite their promising performance, deep networks have shown sensitivities to perturbations of their inputs (e.g., adversarial examples) and their…
Analog in-memory computing (AIMC) accelerators enable efficient deep neural network computation directly within memory using resistive crossbar arrays, where model parameters are represented by the conductance states of memristive devices.…
We present and experimentally evaluate using transfer learning to address experimental data scarcity when training neural network (NN) models for Mach-Zehnder interferometer mesh-based optical matrix multipliers. Our approach involves…
Convolutional Neural Networks (CNNs) are central to modern AI, but their performance is often limited by hardware constraints. NVIDIA Tensor Cores, for instance, require input channels to be multiples of 8 and sometimes 512 for efficient…
Machine learning model weights and activations are represented in full-precision during training. This leads to performance degradation in runtime when deployed on neural network accelerator (NNA) chips, which leverage highly parallelized…
Training deep neural networks (DNNs) is computationally expensive, which is problematic especially when performing duplicated or similar training runs in model ensemble or fine-tuning pre-trained models, for example. Once we have trained…
State-of-the-art object recognition Convolutional Neural Networks (CNNs) are shown to be fooled by image agnostic perturbations, called universal adversarial perturbations. It is also observed that these perturbations generalize across…
The ever-increasing data rates of modern communication systems lead to severe distortions of the communication signal, imposing great challenges to state-of-the-art signal processing algorithms. In this context, neural network (NN)-based…
Owing to the data explosion and rapid development of artificial intelligence (AI), particularly deep neural networks (DNNs), the ever-increasing demand for large-scale matrix-vector multiplication has become one of the major issues in…
Neural networks are one of the disruptive computing concepts of our time. However, they fundamentally differ from classical, algorithmic computing in a number of fundamental aspects. These differences result in equally fundamental, severe…
Error correction code is a major part of the communication physical layer, ensuring the reliable transfer of data over noisy channels. Recently, neural decoders were shown to outperform classical decoding techniques. However, the existing…
AI models are essential in science and engineering, but recent advances are pushing the limits of traditional digital hardware. To address these limitations, physical neural networks (PNNs), which use physical substrates for computation,…
Training deep neural network classifiers that are certifiably robust against adversarial attacks is critical to ensuring the security and reliability of AI-controlled systems. Although numerous state-of-the-art certified training methods…
As the size and ubiquity of artificial intelligence and computational machine learning (ML) models grow, their energy consumption for training and use is rapidly becoming economically and environmentally unsustainable. Neuromorphic…
Existing video recognition algorithms always conduct different training pipelines for inputs with different frame numbers, which requires repetitive training operations and multiplying storage costs. If we evaluate the model using other…
Artificial Neural Networks are computational network models inspired by signal processing in the brain. These models have dramatically improved the performance of many learning tasks, including speech and object recognition. However,…