On a recent commute to work, I texted my distant family about our fantasy baseball league, which was nice because I felt connected to them for a second. Then I switched apps and became enraged by a stupid opinion I saw on X, which I shouldn't be using anymore due to its advanced toxicity and mind-numbing inanity. Many minutes passed before I was able to stop reading the stupid replies to the stupid original post and relax the muscles of my face. This is the duality of the phone: It connects me to my loved ones, and sometimes I think it's ruining my life. I need it and I want it, but sometimes I hate it and I fear it.

Existing hardware-aware NAS (HW-NAS) methods typically assume access to precise information circa the target device, either via analytical approximations of the post-compilation latency model, or through learned latency predictors. Such approximate approaches risk introducing estimation errors that may prove detrimental in risk-sensitive applications. In this work, we propose a two-stage HW-NAS framework, in which we first learn an architecture controller on a distribution of synthetic devices, and then directly deploy the controller on a target device. At test-time, our network controller deploys directly to the target device without relying on any pre-collected information, and only exploits direct interactions. In particular, the pre-training phase on synthetic devices enables the controller to design an architecture for the target device by interacting with it through a small number of high-fidelity latency measurements. To guarantee accessibility of our method, we only train our controller with training-free accuracy proxies, allowing us to scale the meta-training phase without incurring the overhead of full network training. We benchmark on HW-NATS-Bench, demonstrating that our method generalizes to unseen devices and searches for latency-efficient architectures by in-context adaptation using only a few real-world latency evaluations at test-time.

Deep learning-based fingerprinting is one of the current promising technologies for outdoor localization in cellular networks. However, deploying such localization systems for heterogeneous phones affects their accuracy as the cellular received signal strength (RSS) readings vary for different types of phones. In this paper, we introduce a number of techniques for addressing the phones heterogeneity problem in the deep-learning based localization systems. The basic idea is either to approximate a function that maps the cellular RSS measurements between different devices or to transfer the knowledge across them. Evaluation of the proposed techniques using different Android phones on four independent testbeds shows that our techniques can improve the localization accuracy by more than 220% for the four testbeds as compared to the state-of-the-art systems. This highlights the promise of the proposed device heterogeneity handling techniques for enabling a wide deployment of deep learning-based localization systems over different devices.

While the use of the Internet of Things is becoming more and more popular, many security vulnerabilities are emerging with the large number of devices being introduced to the market. In this environment, IoT device identification methods provide a preventive security measure as an important factor in identifying these devices and detecting the vulnerabilities they suffer from. In this study, we present a method that identifies devices in the Aalto dataset using the convolutional neural network (CNN). While the use of the Internet of Things is becoming more and more popular, many security vulnerabilities are emerging with the large number of devices being introduced to the market. In this environment, IoT device identification methods provide a preventive security measure as an important factor in identifying these devices and detecting the vulnerabilities they suffer from.

Researchers from Google, Amazon Web Services, UC Berkeley, Shanghai Jiao Tong University, Duke University and Carnegie Mellon University have published a paper titled "Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning" at OSDI 2022. The paper introduces a new method for automating the complex process of parallelising a model with only one line of code. So how does Alpa work? Data parallelism is a technique where model weights are duplicated across accelerators while only partitioning and distributing the training data. The dataset is split into'N' parts in data parallelism with'N' being the quantity of GPUs.

In recent years, we have witnessed the success of deep learning across multiple domains. But we have also seen that due to the large size and computational complexities of the models and data, the performance of the deep learning procedures is reduced. To improve the performance of these models, parallel and distributed deep learning approaches have been introduced. In this article, we are going to discuss parallel and distributed deep learning methods in detail and will try to understand how they help in speeding up the deep learning process. The major points to be discussed in this article are listed below.

Every month, Amazon pushes a slate of updates to its Alexa-enabled devices. One of the more noteworthy features Amazon added this month is the ability to move music between Echo devices using your voice. If you want to do so between different speakers in your home, say "Alexa, pause" to the one currently playing music, and then say "Alexa, resume music here" to the device where you want to move your tunes to. The feature also works with Echo Buds and Echo Auto, allowing you to take your music on the go. If you're a football fan with an Echo Show, another new feature allows you to ask Alexa to play the Two-Minute drill, an NFL pregame show that will offer expert analysis on the next match your favorite team is about to play.

Deep Learning (DL) have greatly contributed to bioelectric signals processing, in particular to extract physiological markers. However, the efficacy and applicability of the results proposed in the literature is often constrained to the population represented by the data used to train the models. In this study, we investigate the issues related to applying a DL model on heterogeneous datasets. In particular, by focusing on heart beat detection from Electrocardiogram signals (ECG), we show that the performance of a model trained on data from healthy subjects decreases when applied to patients with cardiac conditions and to signals collected with different devices. We then evaluate the use of Transfer Learning (TL) to adapt the model to the different datasets. In particular, we show that the classification performance is improved, even with datasets with a small sample size. These results suggest that a greater effort should be made towards generalizability of DL models applied on bioelectric signals, in particular by retrieving more representative datasets.

Since the list has gotten rather long, I have included an excerpt above; the full list is at the bottom of this post. At the entry level, the datasets used are small. Often, they easily fit into the main memory. If they don't already come pre-processed then it's only a few lines of code to apply such operations. Mainly you'll do so for the major domains Audio, Image, Time-series, and Text. Before diving into the large field of Deep Learning it's a good choice to study the basic techniques.

Federated learning (FL) is a highly pursued machine learning technique that can train a model centrally while keeping data distributed. Distributed computation makes FL attractive for bandwidth limited applications especially in wireless communications. There can be a large number of distributed edge devices connected to a central parameter server (PS) and iteratively download/upload data from/to the PS. Due to the limited bandwidth, only a subset of connected devices can be scheduled in each round. There are usually millions of parameters in the state-of-art machine learning models such as deep learning, resulting in a high computation complexity as well as a high communication burden on collecting/distributing data for training. To improve communication efficiency and make the training model converge faster, we propose a new scheduling policy and power allocation scheme using non-orthogonal multiple access (NOMA) settings to maximize the weighted sum data rate under practical constraints during the entire learning process. NOMA allows multiple users to transmit on the same channel simultaneously. The user scheduling problem is transformed into a maximum-weight independent set problem that can be solved using graph theory. Simulation results show that the proposed scheduling and power allocation scheme can help achieve a higher FL testing accuracy in NOMA based wireless networks than other existing schemes.