Related papers: AdANNS: A Framework for Adaptive Semantic Search

Analog computing has reemerged as a promising avenue for accelerating deep neural networks (DNNs) due to its potential to overcome the energy efficiency and scalability challenges posed by traditional digital architectures. However,…

Adaptive inference is an effective mechanism to achieve a dynamic tradeoff between accuracy and computational cost in deep networks. Existing works mainly exploit architecture redundancy in network depth or width. In this paper, we focus on…

Recognizing text in the wild is a really challenging task because of complex backgrounds, various illuminations and diverse distortions, even with deep neural networks (convolutional neural networks and recurrent neural networks). In the…

Recently, dynamic inference has emerged as a promising way to reduce the computational cost of deep convolutional neural network (CNN). In contrast to static methods (e.g. weight pruning), dynamic inference adaptively adjusts the inference…

Despite the empirical success of neural architecture search (NAS) in deep learning applications, the optimality, reproducibility and cost of NAS schemes remain hard to assess. In this paper, we propose Generative Adversarial NAS (GA-NAS)…

The recent ground-breaking advances in deep learning networks ( DNNs ) make them attractive for embedded systems. However, it can take a long time for DNNs to make an inference on resource-limited embedded devices. Offloading the…

Automatic methods for generating state-of-the-art neural network architectures without human experts have generated significant attention recently. This is because of the potential to remove human experts from the design loop which can…

Deep neural networks are getting larger. Their implementation on edge and IoT devices becomes more challenging and moved the community to design lighter versions with similar performance. Standard automatic design tools such as…

Artificial Neural Networks (ANNs) are bio-inspired models of neural computation that have proven highly effective. Still, ANNs lack a natural notion of time, and neural units in ANNs exchange analog values in a frame-based manner, a…

Artificial neural network (NN) architecture design is a nontrivial and time-consuming task that often requires a high level of human expertise. Neural architecture search (NAS) serves to automate the design of NN architectures and has…

Modelling the complex physics of the Interstellar Medium (ISM) in the context of large-scale numerical simulations is a challenging task. A number of methods have been proposed to embed a description of the ISM into different codes. We…

Semantic segmentation has made much progress with increasingly powerful pixel-wise classifiers and incorporating structural priors via Conditional Random Fields (CRF) or Generative Adversarial Networks (GAN). We propose a simpler…

Analog In-memory Computing (AIMC) has emerged as a highly efficient paradigm for accelerating Deep Neural Networks (DNNs), offering significant energy and latency benefits over conventional digital hardware. However, state-of-the-art neural…

Neural processes (NPs) learn stochastic processes and predict the distribution of target output adaptively conditioned on a context set of observed input-output pairs. Furthermore, Attentive Neural Process (ANP) improved the prediction…

Recent advances in Neural Architecture Search (NAS) such as one-shot NAS offer the ability to extract specialized hardware-aware sub-network configurations from a task-specific super-network. While considerable effort has been employed…

Dense retrieval represents queries and documents as high-dimensional embeddings, but these representations can be redundant at the query level: for a given information need, only a subset of dimensions is consistently helpful for ranking.…

Vector databases typically rely on approximate nearest neighbor (ANN) search to retrieve the top-k closest vectors to a query in embedding space. While effective, this approach often yields semantically redundant results, missing the…

Storing and processing of embedding vectors by specialized Vector databases (VDBs) has become the linchpin in building modern AI pipelines. Most current VDBs employ variants of a graph-based ap- proximate nearest-neighbor (ANN) index…

Implicit neural representations are powerful for geometric modeling, but their practical use is often limited by the high computational cost of network evaluations. We observe that implicit representations require progressively lower…

We study the Approximate Nearest Neighbor (ANN) problem under a powerful adaptive adversary that controls both the dataset and a sequence of $Q$ queries. Primarily, for the high-dimensional regime of $d = \omega(\sqrt{Q})$, we introduce a…