In this paper, we present a novel framework for enhancing the performance of Quanvolutional Neural Networks (QuNNs) by introducing trainable quanvolutional layers and addressing the critical challenges associated with them. Traditional quanvolutional layers, although beneficial for feature extraction, have largely been static, offering limited adaptability. Unlike state-of-the-art, our research overcomes this limitation by enabling training within these layers, significantly increasing the flexibility and potential of QuNNs. However, the introduction of multiple trainable quanvolutional layers induces complexities in gradient-based optimization, primarily due to the difficulty in accessing gradients across these layers. To resolve this, we propose a novel architecture, Residual Quanvolutional Neural Networks (ResQuNNs), leveraging the concept of residual learning, which facilitates the flow of gradients by adding skip connections between layers. By inserting residual blocks between quanvolutional layers, we ensure enhanced gradient access throughout the network, leading to improved training performance. Moreover, we provide empirical evidence on the strategic placement of these residual blocks within QuNNs. Through extensive experimentation, we identify an efficient configuration of residual blocks, which enables gradients across all the layers in the network that eventually results in efficient training. Our findings suggest that the precise location of residual blocks plays a crucial role in maximizing the performance gains in QuNNs. Our results mark a substantial step forward in the evolution of quantum deep learning, offering new avenues for both theoretical development and practical quantum computing applications.

Recent years have seen a large interest in using the Simplified Molecular Input Line Entry System (SMILES) chemical language as input for deep learning architectures solving chemical tasks. Many successful applications have been demonstrated within de novo molecular design, quantitative structure-activity relationship modelling, forward reaction prediction and single-step retrosynthetic planning as examples. PySMILESUtils aims to enable these tasks by providing readyto- use and adaptable Python classes for tokenization, augmentation, dataset, and dataloader creation. Classes for handling datasets larger than memory and speeding up training by minimizing padding are also provided. The framework subclasses PyTorch dataset and dataloaders but should be adaptable for other deep learning frameworks.

Many state of the art deep learning models have hefty compute, storage and power consumption requirements which make them impractical or difficult to use on resource-constrained devices. In this tech talk, you'll learn why Apache MXNet, an open Source library for Deep Learning, is IoT-friendly in many ways. In addition, you'll learn how services like AWS Lambda and AWS Greengrass make it easy to deploy MXNet models on edge devices.

Deep learning can enable Internet of Things (IoT) devices to interpret unstructured multimedia data and intelligently react to both user and environmental events but has demanding performance and power requirements. The authors explore two ways to successfully integrate deep learning with low-power IoT products.

Andrew Ng 50,482 views Location Based Services (video 5/8) - Duration: 3:58.