arXiv subjects

Sandip Halder

Publications and source records attributed to Sandip Halder.

27 records · Page 2Linked to original sources

arXiv2023

SEMI-CenterNet: A Machine Learning Facilitated Approach for Semiconductor Defect Inspection

Continual shrinking of pattern dimensions in the semiconductor domain is making it increasingly difficult to inspect defects due to factors such as the presence of stochastic noise and the dynamic behavior of defect patterns and types. Conventional rule-based methods and non-parametric supervised machine learning algorithms like KNN mostly fail at the requirements of semiconductor defect inspection at these advanced nodes. Deep Learning (DL)-based methods have gained popularity in the semiconductor defect inspection domain because they have been proven robust towards these challenging scenarios. In this research work, we have presented an automated DL-based approach for efficient localization and classification of defects in SEM images. We have proposed SEMI-CenterNet (SEMI-CN), a customized CN architecture trained on SEM images of semiconductor wafer defects. The use of the proposed CN approach allows improved computational efficiency compared to previously studied DL models. SEMI-CN gets trained to output the center, class, size, and offset of a defect instance. This is different from the approach of most object detection models that use anchors for bounding box prediction. Previous methods predict redundant bounding boxes, most of which are discarded in postprocessing. CN mitigates this by only predicting boxes for likely defect center points. We train SEMI-CN on two datasets and benchmark two ResNet backbones for the framework. Initially, ResNet models pretrained on the COCO dataset undergo training using two datasets separately. Primarily, SEMI-CN shows significant improvement in inference time against previous research works. Finally, transfer learning (using weights of custom SEM dataset) is applied from ADI dataset to AEI dataset and vice-versa, which reduces the required training time for both backbones to reach the best mAP against conventional training method.

cs.CV↗

arXiv2023

YOLOv8 for Defect Inspection of Hexagonal Directed Self-Assembly Patterns: A Data-Centric Approach

Shrinking pattern dimensions leads to an increased variety of defect types in semiconductor devices. This has spurred innovation in patterning approaches such as Directed self-assembly (DSA) for which no traditional, automatic defect inspection software exists. Machine Learning-based SEM image analysis has become an increasingly popular research topic for defect inspection with supervised ML models often showing the best performance. However, little research has been done on obtaining a dataset with high-quality labels for these supervised models. In this work, we propose a method for obtaining coherent and complete labels for a dataset of hexagonal contact hole DSA patterns while requiring minimal quality control effort from a DSA expert. We show that YOLOv8, a state-of-the-art neural network, achieves defect detection precisions of more than 0.9 mAP on our final dataset which best reflects DSA expert defect labeling expectations. We discuss the strengths and limitations of our proposed labeling approach and suggest directions for future work in data-centric ML-based defect inspection.

cs.CV↗

arXiv2023

Interfacial-antiferromagnetic-coupling driven magneto-transport properties in ferromagnetic superlattices

We explore the role of interfacial antiferromagnetic interaction in coupled soft and hard ferromagnetic layers to ascribe the complex variety of magneto-transport phenomena observed in $La_{0.7}Sr_{0.3}MnO_3/SrRuO_3$ (LSMO/SRO) superlattices (SLs) within a one-band double exchange model using Monte-Carlo simulations. Our calculations incorporate the magneto-crystalline anisotropy interactions and super-exchange interactions of the constituent materials, and two types of antiferromagnetic interactions between Mn and Ru ions at the interface: (i) carrier-driven and (ii) Mn-O-Ru bond super-exchange in the model Hamiltonian to investigate the properties along the hysteresis loop. We find that the antiferromagnetic coupling at the interface induces the LSMO and SRO layers to align in anti-parallel orientation at low temperatures. Our results reproduce the positive exchange bias of the minor loop and inverted hysteresis loop of LSMO/SRO SL at low temperatures as reported in experiments. In addition, conductivity calculations show that the carrier-driven antiferromagnetic coupling between the two ferromagnetic layers steers the SL towards a metallic (insulating) state when LSMO and SRO are aligned in anti-parallel (parallel) configuration, in good agreement with the experimental data. This demonstrate the necessity of carrier-driven antiferromagnetic interactions at the interface to understand the one-to-one correlation between the magnetic and transport properties observed in experiments. For high temperature, just below the ferromagnetic $T_C$ of SRO, we unveiled the unconventional three-step flipping process along the magnetic hysteresis loop. We emphasize the key role of interfacial antiferromagnetic coupling between LSMO and SRO to understand these multiple-step flipping processes along the hysteresis loop.

cond-mat.str-el↗

arXiv2023

A Deep Learning Framework for Verilog Autocompletion Towards Design and Verification Automation

Innovative Electronic Design Automation (EDA) solutions are important to meet the design requirements for increasingly complex electronic devices. Verilog, a hardware description language, is widely used for the design and verification of digital circuits and is synthesized using specific EDA tools. However, writing code is a repetitive and time-intensive task. This paper proposes, primarily, a novel deep learning framework for training a Verilog autocompletion model and, secondarily, a Verilog dataset of files and snippets obtained from open-source repositories. The framework involves integrating models pretrained on general programming language data and finetuning them on a dataset curated to be similar to a target downstream task. This is validated by comparing different pretrained models trained on different subsets of the proposed Verilog dataset using multiple evaluation metrics. These experiments demonstrate that the proposed framework achieves better BLEU, ROUGE-L, and chrF scores by 9.5%, 6.7%, and 6.9%, respectively, compared to a model trained from scratch. Code and data are made available at: https://github.com/99EnriqueD/verilog_autocompletion .

cs.LG↗

arXiv2023

Tailoring the interfacial magnetic interaction in epitaxial La$_{0.7}$Sr$_{0.3}$MnO$_3$/Sm$_{0.5}$Ca$_{0.5}$MnO$_3$ heterostructures

Interface engineering in complex oxide heterostructures has developed into a flourishing field as various intriguing physical phenomena can be demonstrated which are otherwise absent in their constituent bulk compounds. Here we present La$_{0.7}$Sr$_{0.3}$MnO$_3$ (LSMO) / Sm$_{0.5}$Ca$_{0.5}$MnO$_3$ (SCMO) based heterostructures showcasing the dominance of antiferromagnetic interaction with increasing interfaces. In particular, we demonstrate that exchange bias can be tuned by increasing the number of interfaces; while, on the other hand, electronic phase separation can be mimicked by creating epitaxial multilayers of such robust charge ordered antiferromagnetic (CO-AF) and ferromagnetic (FM) manganites with increased AF nature, which otherwise would require intrinsically disordered mixed phase materials. The origin of these phenomena is discussed in terms of magnetic interactions between the interfacial layers of the LSMO/SCMO. A theoretical model has been utilized to account for the experimentally observed magnetization curves in order to draw out the complex interplay between FM and AF spins at interfaces with the onset of charge ordering.

cond-mat.mtrl-sci↗

arXiv2023

SEMI-PointRend: Improved Semiconductor Wafer Defect Classification and Segmentation as Rendering

In this study, we applied the PointRend (Point-based Rendering) method to semiconductor defect segmentation. PointRend is an iterative segmentation algorithm inspired by image rendering in computer graphics, a new image segmentation method that can generate high-resolution segmentation masks. It can also be flexibly integrated into common instance segmentation meta-architecture such as Mask-RCNN and semantic meta-architecture such as FCN. We implemented a model, termed as SEMI-PointRend, to generate precise segmentation masks by applying the PointRend neural network module. In this paper, we focus on comparing the defect segmentation predictions of SEMI-PointRend and Mask-RCNN for various defect types (line-collapse, single bridge, thin bridge, multi bridge non-horizontal). We show that SEMI-PointRend can outperforms Mask R-CNN by up to 18.8% in terms of segmentation mean average precision.

cs.CV↗

arXiv2023

Optimizing YOLOv7 for Semiconductor Defect Detection

The field of object detection using Deep Learning (DL) is constantly evolving with many new techniques and models being proposed. YOLOv7 is a state-of-the-art object detector based on the YOLO family of models which have become popular for industrial applications. One such possible application domain can be semiconductor defect inspection. The performance of any machine learning model depends on its hyperparameters. Furthermore, combining predictions of one or more models in different ways can also affect performance. In this research, we experiment with YOLOv7, a recently proposed, state-of-the-art object detector, by training and evaluating models with different hyperparameters to investigate which ones improve performance in terms of detection precision for semiconductor line space pattern defects. The base YOLOv7 model with default hyperparameters and Non Maximum Suppression (NMS) prediction combining outperforms all RetinaNet models from previous work in terms of mean Average Precision (mAP). We find that vertically flipping images randomly during training yields a 3% improvement in the mean AP of all defect classes. Other hyperparameter values improved AP only for certain classes compared to the default model. Combining models that achieve the best AP for different defect classes was found to be an effective ensembling strategy. Combining predictions from ensembles using Weighted Box Fusion (WBF) prediction gave the best performance. The best ensemble with WBF improved on the mAP of the default model by 10%.

cs.CV↗

arXiv2022

Deep Learning based Defect classification and detection in SEM images: A Mask R-CNN approach

In this research work, we have demonstrated the application of Mask-RCNN (Regional Convolutional Neural Network), a deep-learning algorithm for computer vision and specifically object detection, to semiconductor defect inspection domain. Stochastic defect detection and classification during semiconductor manufacturing has grown to be a challenging task as we continuously shrink circuit pattern dimensions (e.g., for pitches less than 32 nm). Defect inspection and analysis by state-of-the-art optical and e-beam inspection tools is generally driven by some rule-based techniques, which in turn often causes to misclassification and thereby necessitating human expert intervention. In this work, we have revisited and extended our previous deep learning-based defect classification and detection method towards improved defect instance segmentation in SEM images with precise extent of defect as well as generating a mask for each defect category/instance. This also enables to extract and calibrate each segmented mask and quantify the pixels that make up each mask, which in turn enables us to count each categorical defect instances as well as to calculate the surface area in terms of pixels. We are aiming at detecting and segmenting different types of inter-class stochastic defect patterns such as bridge, break, and line collapse as well as to differentiate accurately between intra-class multi-categorical defect bridge scenarios (as thin/single/multi-line/horizontal/non-horizontal) for aggressive pitches as well as thin resists (High NA applications). Our proposed approach demonstrates its effectiveness both quantitatively and qualitatively.

cs.CV↗

arXiv2022

Itinerant ferromagnetism in a spin-fermion model for diluted spin systems

We investigate the itinerant ferromagnetism using a diluted spin-fermion model, derived from a repulsive Hubbard model, where itinerant fermions are coupled antiferromagnetically to auxiliary fields in a three-dimensional simple cubic lattice. We focus, in particular, on understanding the spin-dependent transport properties of the itinerant fermions in the impurity band by taking positional disorder of the auxiliary fields into account. For on-site repulsion $U$ $\sim$ bandwidth the density of the itinerant carriers confined to the impurity band, play a key role in determining the kinetic energy of the system and consequently the carrier spin polarization. Our semi-classical Monte Carlo calculations show that the ferromagnetic transition temperature of the carrier spins indeed shows an optimization behavior with the carrier density. We calculate the transport properties in details to establish a one-to-one correspondence between the magnetic and transport properties of the carriers. Our results obtained beyond the perturbative regime are significant for understanding the ferromagnetism in diluted magnetic semiconductors.

cond-mat.str-el↗