Multilayer Perceptron (MLP) is a simple practice of Neural Network (NN) and the cornerstone of research and development of deep learning. Each neuron is connected to all neurons in the previous layer and implements a non-linear mapping through activation functions. MLP can learn complex non-linear relationships among features through the superposition of multiple hidden layers, but it still cannot discover the inherent strong correlation among features. The reason is that each neuron uses a simple weighted summation method to organize all the neurons in the previous layer. Inspired by quantum theory, this paper builds a non-linear NN layer that can mine strong correlations among features based on multi-body quantum systems, and then constructs a multi-layer perceptron, called Quantum-inspired MLP (QiMLP). It is conceivable that QiMLP will have important inspirational significance in reshaping machine learning, deep learning and large language models. We theoretically analyzed the basis for QiMLP to mine strong correlations among features, and implemented experiments on multiple classic deep learning datasets. Experimental results verify that QiMLP not only learns strong correlations among features, but also significantly reduces the number of parameters with hundreds of times improvement.

Ribonucleic acid (RNA) molecules are essential macromolecules that perform diverse biological functions in living beings. Precise prediction of RNA secondary structures is instrumental in deciphering their complex three-dimensional architecture and functionality. Traditional methodologies for RNA structure prediction, including energy-based and learning-based approaches, often depict RNA secondary structures from a static perspective and rely on stringent a priori constraints. Inspired by the success of diffusion models, in this work, we introduce RNADiffFold, an innovative generative prediction approach of RNA secondary structures based on multinomial diffusion. We reconceptualize the prediction of contact maps as akin to pixel-wise segmentation and accordingly train a denoising model to refine the contact maps starting from a noise-infused state progressively. We also devise a potent conditioning mechanism that harnesses features extracted from RNA sequences to steer the model toward generating an accurate secondary structure. These features encompass one-hot encoded sequences, probabilistic maps generated from a pre-trained scoring network, and embeddings and attention maps derived from RNA foundation model. Experimental results on both within- and cross-family datasets demonstrate RNADiffFold's competitive performance compared with current state-of-the-art methods. Additionally, RNADiffFold has shown a notable proficiency in capturing the dynamic aspects of RNA structures, a claim corroborated by its performance on datasets comprising multiple conformations.

Multiple instance learning (MIL) has been successfully applied for whole slide images (WSIs) analysis in computational pathology, enabling a wide range of prediction tasks from tumor subtyping to inferring genetic mutations and multi-omics biomarkers. However, existing MIL methods predominantly focus on single-task learning, resulting in not only overall low efficiency but also the overlook of inter-task relatedness. To address these issues, we proposed an adapted architecture of Multi-gate Mixture-of-experts with Multi-proxy for Multiple instance learning (M4), and applied this framework for simultaneous prediction of multiple genetic mutations from WSIs. The proposed M4 model has two main innovations: (1) adopting a multi-gate mixture-of-experts strategy for multiple genetic mutation simultaneous prediction on a single WSI; (2) introducing a multi-proxy CNN construction on the expert and gate networks to effectively and efficiently capture patch-patch interactions from WSI. Our model achieved significant improvements across five tested TCGA datasets in comparison to current state-of-the-art single-task methods. The code is available at: https://github.com/Bigyehahaha/M4.

Aptamers are single-stranded nucleic acid ligands, featuring high affinity and specificity to target molecules. Traditionally they are identified from large DNA/RNA libraries using $in vitro$ methods, like Systematic Evolution of Ligands by Exponential Enrichment (SELEX). However, these libraries capture only a small fraction of theoretical sequence space, and various aptamer candidates are constrained by actual sequencing capabilities from the experiment. Addressing this, we proposed AptaDiff, the first in silico aptamer design and optimization method based on the diffusion model. Our Aptadiff can generate aptamers beyond the constraints of high-throughput sequencing data, leveraging motif-dependent latent embeddings from variational autoencoder, and can optimize aptamers by affinity-guided aptamer generation according to Bayesian optimization. Comparative evaluations revealed AptaDiff's superiority over existing aptamer generation methods in terms of quality and fidelity across four high-throughput screening data targeting distinct proteins. Moreover, surface plasmon resonance experiments were conducted to validate the binding affinity of aptamers generated through Bayesian optimization for two target proteins. The results unveiled a significant boost of $87.9\%$ and $60.2\%$ in RU values, along with a 3.6-fold and 2.4-fold decrease in KD values for the respective target proteins. Notably, the optimized aptamers demonstrated superior binding affinity compared to top experimental candidates selected through SELEX, underscoring the promising outcomes of our AptaDiff in accelerating the discovery of superior aptamers.

Compared to conventional speech synthesis, end-to-end speech synthesis has achieved much better naturalness with more simplified system building pipeline. End-to-end framework can generate natural speech directly from characters for English. But for other languages like Chinese, recent studies have indicated that extra engineering features are still needed for model robustness and naturalness, e.g, word boundaries and prosody boundaries, which makes the front-end pipeline as complicated as the traditional approach. To maintain the naturalness of generated speech and discard language-specific expertise as much as possible, in Mandarin TTS, we introduce a novel self-attention based encoder with learnable Gaussian bias in Tacotron. We evaluate different systems with and without complex prosody information and results show that the proposed approach has the ability to generate stable and natural speech with minimum language-dependent front-end modules.

The rule-based parsing is a prevalent method for the natural language understanding (NLU) and has been introduced in dialogue systems for spoken language processing (SLP). However, additional measures must be taken to cope with the severe spoken linguistic phenomena, such as garbage, repetition, ellipsis, word disordering, fragment and ill form, which frequently occur in the spoken language. We propose in this paper a robust parsing scheme, which integrates the following methods. Keywords are used as terminal symbols; hence the symbol set of the grammar is purely within the semantical category. The definition of the grammar is extended to accommodate four types of rules, called up-tying, by-passing, up-messing, and over-crossing respectively. An improved chart parser, named marionette, is designed to parse the semantic grammar instance. The robust parsing scheme has been adopted in an air traveling information service system, called EasyFlight, and has achieved a high performance when dealing with the spontaneous speech. 1.

In this paper we present the design and the implement of the language understanding component of a Chinese spoken language dialogue system EasyNav. In pursuing the coherence with the goal of understanding, we design the structure of system with speech decoding and language understanding integrated closely. Thus the language understanding component need to be restrictive besides portable. Actually we implement a general syntactic parser and domain-specific semantic parser for the purpose. The grammar rules written for understanding are suitable for spoken language. The feature of spoken language also exists throughout the system. 1.