Machine LearningOur Machine Learning team has been at the forefront of machine learning developments, including deep learning, support vector machines, and semantic analysis, for over a decade. We develop innovative technologies integrated into NEC’s products and services. Machine learning is the critical technology for data analytics and artificial intelligence. Recent progress in this field opens opportunities for various new applications.

Deep learning will maintain prominence with more robust model architectures, training methods, and optimization techniques. Enhanced interpretability and explainability will be imperative, especially for AI systems in critical domains like healthcare and finance. Addressing bias and ensuring fairness in AI algorithms will be a top priority, leading to the development of tools and guidelines for ethical AI. Federated learning, quantum computing’s potential impact, and the growth of edge computing will diversify ML applications.

Natural language processing will continue to advance, driving progress in conversational AI, while healthcare, finance, education, and creative industries will witness profound AI integration. As quantum computing matures, it could revolutionize machine learning, while edge computing and federated learning will expand AI’s reach across various domains. Our machine learning research will produce innovation across industries, including more accurate medical diagnoses, safer autonomous systems, and efficient energy use while enabling personalized education and AI-generated creativity.

Read our news and publications from our world-class team of researchers from our Machine Learning department.

Posts

On Synthesizing Data for Context Attribution in Question Answering

/in /by

Question Answering (QA) accounts for a significantportion of LLM usage “in the wild”.However, LLMs sometimes produce false ormisleading responses, also known as hallucinations.Therefore, grounding the generatedanswers in contextually provided information—i.e., providing evidence for the generated text—is paramount for LLMs’ trustworthiness. Providingthis information is the task of context attribution.In this paper, we systematically studyLLM-based approaches for this task, namelywe investigate (i) zero-shot inference, (ii) LLMensembling, and (iii) fine-tuning of small LMson synthetic data generated by larger LLMs.Our key contribution is SYNQA: a novel generativestrategy for synthesizing context attributiondata. Given selected context sentences, anLLM generates QA pairs that are supported bythese sentences. This leverages LLMs’ naturalstrengths in text generation while ensuring clearattribution paths in the synthetic training data.We show that the attribution data synthesizedvia SYNQA is highly effective for fine-tuningsmall LMs for context attribution in differentQA tasks and domains. Finally, with a userstudy, we validate the usefulness of small, efficientLMs (fine-tuned on synthetic data fromSYNQA) in context attribution for QA.

Read more

Group Relative Augmentation for Data Efficient Action Detection

/in /by

Adapting large Video-Language Models (VLMs) for action detection using only a few examples poses challenges like overfitting and the granularity mismatch between scene-level pre-training and required person-centric understanding. We propose an efficient adaptation strategy combining parameter-efficient tuning (LoRA) with a novel learnable internal feature augmentation. Applied within the frozen VLM backbone using FiLM, these augmentations generate diverse feature variations directly relevant to the task. Additionally, we introduce a group-weighted loss function that dynamically modulates the training contribution of each augmented sample based on its prediction divergence relative to the group average. This promotes robust learning by prioritizing informative yet reasonable augmentations. We demonstrate our method’s effectiveness on complex multi-label, multi-person action detection datasets (AVA, MOMA), achieving strong mAP performance and showcasing significant data efficiency for adapting VLMs from limited examples.

Read more

Quantitative Bounds for Length Generalization in Transformers

/in /by

We provide quantitative bounds on the length of sequences required to be observed during training for a transformer to length generalize, e.g., to continue to perform well on sequences unseen during training. Our results improve on Huang et al. [8], who show that there is a finite training length beyond which length generalization is guaranteed, but for which they do not provide quantitative bounds.

Read more

PPDiff: Diffusing in Hybrid Sequence-Structure Space for Protein-Protein Complex Design

/in /by

Designing protein-binding proteins with high affinity is critical in biomedical research and biotechnology. Despite recent advancements targeting specific proteins, the ability to create high-affinity binders for arbitrary protein targets on demand, without extensive rounds of wet-lab testing,remains a significant challenge. Here, we introduce PPDiff, a diffusion model to jointly design the sequence and structure of binders for arbitrary protein targets in a non-autoregressive manner. PPDiff builds upon our developed Sequence Structure Interleaving Network with Causal attention layers (SSINC), which integrates interleaved self-attention layers to capture global amino acid correlations, k-nearest neighbor (kNN) equivariant graph layers to model local interactions in three-dimensional (3D) space, and causal attention layers to simplify the intricate interdependencies within the protein sequence. To assess PPDiff, we curate PPBench, a general protein complex dataset comprising 706,360 complexes from the Protein Data Bank (PDB). The model is pretrained on PPBench and finetuned on two real-world applications: target-protein mini-binder complex design and antigen-antibody complex design. PPDiff consistently surpasses baseline methods, achieving success rates of 50.00%, 23.16%, and 16.89% for the pretraining task and the two downstream applications, respectively.

Read more

Pathologist-Read vs AI-Driven Assessment of Tumor-Infiltrating Lymphocytes in Melanoma

/in /by

Tumor-infiltrating lymphocytes (TILs) are a provocative biomarker in melanoma, influencing diagnosis, prognosis, and immunotherapy outcomes; however, traditional pathologistreadTIL assessment on hematoxylin and eosin–stained slides is prone to interobserver variability, leading to inconsistent clinical decisions. Therefore, development of newer TIL scoring approachesthat produce more reliable and consistent readouts is important.

Read more

Solving Inverse Problems via a Score-Based Prior: An Approximation-Free Posterior Sampling Approach

/in /by

Diffusion models (DMs) have proven to be effective in modeling high-dimensional distributions, leading to their widespread adoption for representing complex priors in Bayesian inverse problems (BIPs). However, current DM-based posterior sampling methods proposed for solving common BIPs rely on heuristic approximations to the generative process. To exploit the generative capability of DMs and avoid the usage of such approximations, we propose an ensemble-based algorithm that performs posterior sampling without the use of heuristic approximations. Our algorithm is motivated by existing works that combine DM-based methods with the sequential Monte Carlo (SMC) method. By examining how the prior evolves through the diffusion process encoded by the pre-trained score function, we derive a modified partial differential equation (PDE) governing the evolution of the corresponding posterior distribution. This PDE includes a modified diffusion term and a reweighting term, which can be simulated via stochastic weighted particle methods. Theoretically, we prove that the error between the true posterior distribution canbe bounded in terms of the training error of the pre-trained score function and the ]number of particles in the ensemble. Empirically, we validate our algorithm on several inverse problems in imaging to show that our method gives more accurate reconstructions compared to existing DM-based methods.

Read more

CALIBFREE: Self-Supervised Feature Disentanglement for Calibration-Free Multi-Camera Multi-Object Tracking

/in /by

Multi-camera multi-object tracking (MCMOT) faces significant challenges in maintaining consistent object identities across varying camera perspectives, particularly when precise calibration and extensive annotations are required. In this paper, we present CalibFree, a self-supervised representation learning framework that does not need any calibration or manual labeling for the MCMOT task. By promoting feature separation between view-agnostic and view-specific representations through single-view distillation and cross-view reconstruction, our method adapts to complex, dynamic scenarios with minimal overhead. Experiments on the MMP-MvMHAT dataset show a 3% improvement in overall accuracy and a 7.5% increase in the average F1 score over state-of-the-art approaches, confirming the effectiveness of our calibration-free design. Moreover, on the more diverse MvMHAT dataset, our approach demonstrates superior over-time tracking and strong cross-view performance, highlighting its adaptability to a wide range of camera configurations. Code will be publicly available upon acceptance.

Read more

A Quantum Variational Autoencoder Utilizing Regularized Mixed-state Latent Representations

/in /by

A major challenge in near-term quantum computing is its application to large real-world datasets due to scarce quantum hardware resources. One approach to enabling tractable quantum models for such datasets involves finding low-dimensional representations that preserve essential information for downstream analysis. Inclassical machine learning, variational autoencoders (VAEs) facilitate efficient data compression, representationlearning for subsequent tasks, and novel data generation. However, no quantum model has been proposed thatexactly captures all of these features for direct application to quantum data on quantum computers. Some existingquantum models for data compression lack regularization of latent representations, thus preventing direct use forgeneration and control of generalization. Others are hybrid models with only some internal quantum components,impeding direct training on quantum data. To address this, we present a fully quantum framework, ?-QVAE,which encompasses all the capabilities of classical VAEs and can be directly applied to map both classicaland quantum data to a lower-dimensional space, while effectively reconstructing much of the original statefrom it. Our model utilizes regularized mixed states to attain optimal latent representations. It accommodatesvarious divergences for reconstruction and regularization. Furthermore, by accommodating mixed states at everystage, it can utilize the full data density matrix and allow for a training objective defined on probabilisticmixtures of input data. Doing so, in turn, makes efficient optimization possible and has potential implications forprivate and federated learning. In addition to exploring the theoretical properties of ?-QVAE, we demonstrateits performance on representative genomics and synthetic data. Our results indicate that ?-QVAE consistentlylearns representations that better utilize the capacity of the latent space and exhibits similar or better performancecompared with matched classical models.

Read more

Enhancing EDFAs Greybox Modeling in Optical Multiplex Sections Using Few-Shot Learning

/in /by

We combine few-shot learning and grey-box modeling for EDFAs in optical lines, training a single EDFA model on 500 spectral loads and transferring it to other EDFAs using 4-8 samples, maintaining low OSNR prediction error.

Read more

A Smart Sensing Grid for Road Traffic Detection Using Terrestrial Optical Networks and Attention-Enhanced Bi-LSTM

/in /by

We demonstrate the use of existing terrestrial optical networks as a smart sensing grid, employing a bidirectional long short-term memory (Bi-LSTM) model enhanced with an attention mechanism to detect road vehicles. The main idea of our approach is to deploy a fast, accurate and reliable trained deep learning model in each network element that is constantly monitoring the state of polarization (SOP) of data signals traveling through the optical line system (OLS). Consequently, this deployment approach enables the creation of a sensing smart grid that can continuously monitor wide areas and respond with notifications/alerts for road traffic situations. The model is trained on the synthetic dataset and tested on the real dataset obtained from the deployed metropolitan fiber cable in the city of Turin. Our model is able to achieve 99% accuracy for both synthetic and real datasets.

Read more