Related papers: Turbo Autoencoder with a Trainable Interleaver

Recent studies show that auto-encoder based approaches successfully perform language generation, smooth sentence interpolation, and style transfer over unseen attributes using unlabelled datasets in a zero-shot manner. The latent space…

The design of codes for communicating reliably over a statistically well defined channel is an important endeavor involving deep mathematical research and wide-ranging practical applications. In this work, we present the first family of…

End-to-end learning of communication systems with neural networks and particularly autoencoders is an emerging research direction which gained popularity in the last year. In this approach, neural networks learn to simultaneously optimize…

This paper is devoted to the finite-length analysis of turbo decoding over the binary erasure channel (BEC). The performance of iterative belief-propagation (BP) decoding of low-density parity-check (LDPC) codes over the BEC can be…

Building scalable models to learn from diverse, multimodal data remains an open challenge. For vision-language data, the dominant approaches are based on contrastive learning objectives that train a separate encoder for each modality. While…

Recently, Machine Learning (ML) is recognized as an effective tool for wireless communications and plays an evolutionary role to enhance Physical Layer (PHY) of 5th Generation (5G) and Beyond 5G (B5G) systems. In this paper, we focus on the…

In our previous work, we proposed a discriminative autoencoder (DcAE) for speech recognition. DcAE combines two training schemes into one. First, since DcAE aims to learn encoder-decoder mappings, the squared error between the reconstructed…

Power line communication continues to draw increasing interest by promising a wide range of applications including cost-free last-mile communication solution. However, signal transmitted through the power lines deteriorates badly due to the…

Textual graphs are ubiquitous in real-world applications, featuring rich text information with complex relationships, which enables advanced research across various fields. Textual graph representation learning aims to generate…

Traditional mathematical models used in designing next-generation communication systems often fall short due to inherent simplifications, narrow scope, and computational limitations. In recent years, the incorporation of deep learning (DL)…

The omnipresence of deep learning architectures such as deep convolutional neural networks (CNN)s is fueled by the synergistic combination of ever-increasing labeled datasets and specialized hardware. Despite the indisputable success, the…

We propose a topic-guided variational autoencoder (TGVAE) model for text generation. Distinct from existing variational autoencoder (VAE) based approaches, which assume a simple Gaussian prior for the latent code, our model specifies the…

To meet the evolving data rate requirements of emerging wireless communication technologies, many parallel architectures have been proposed to implement high throughput turbo decoders. However, concurrent memory reading/writing in parallel…

As large language models (LLMs) grow in scale and capability, understanding their internal mechanisms becomes increasingly critical. Sparse autoencoders (SAEs) have emerged as a key tool in mechanistic interpretability, enabling the…

Sparse autoencoders (SAEs) extract human-interpretable features from deep neural networks by transforming their activations into a sparse, higher dimensional latent space, and then reconstructing the activations from these latents.…

This paper presents TurboNet, a novel model-driven deep learning (DL) architecture for turbo decoding that combines DL with the traditional max-log-maximum a posteriori (MAP) algorithm. To design TurboNet, we unfold the original iterative…

In this paper, we present an in-depth investigation of the convolutional autoencoder (CAE) bottleneck. Autoencoders (AE), and especially their convolutional variants, play a vital role in the current deep learning toolbox. Researchers and…

Imitation learning is an intuitive approach for teaching motion to robotic systems. Although previous studies have proposed various methods to model demonstrated movement primitives, one of the limitations of existing methods is that the…

Variational Auto-Encoders (VAEs) have been widely applied for learning compact, low-dimensional latent representations of high-dimensional data. When the correlation structure among data points is available, previous work proposed…

We propose TC-AE, a ViT-based architecture for deep compression autoencoders. Existing methods commonly increase the channel number of latent representations to maintain reconstruction quality under high compression ratios. However, this…