Sharif Digital Repository

Supervised kernel learning has been the focus of research in recent years. Although these methods are developed based on rigorous frameworks, they fail to improve the classification accuracy in real world applications. In order to find the origin of this problem, it should be noted that the kernel function represents a prior knowledge on the labeling function. Similar to other learning problem, learning this prior knowledge needs another prior knowledge. In supervised kernel learning, only naive assumptions can be used as the prior knowledge. These include minimizing the ℓ1 and ℓ2 norms of the kernel parameters.
As an alternative approach, in Semi-Supervised Learning (SSL), unlabeled... 

Autoencoder, as an essential part of many anomaly detection methods, is lacking flexibility on normal data in complex datasets. U-Net is proved to be effective for this purpose but overfits on the training data if trained by just using reconstruction error similar to other AE-based frameworks. Puzzle-solving, as a pretext task of self-supervised learning (SSL) methods, has earlier proved its ability in learning semantically meaningful features. We show that training U-Nets based on this task is an effective remedy that prevents overfitting and facilitates learning beyond pixel-level features. Shortcut solutions, however,are a big challenge in SSL tasks, including jigsaw puzzles. We propose... 

Spatial transcriptomics is a new technology that, in addition to transcriptomic cell information, provides spatial information for each of the sample cells and, if possible, histological images of the cells. Despite much research on cell indexing, little research has been done on using cell spatial information to cluster cells, and existing methods can be improved. The aim of this study is to use cell spatial data to extract more information from the samples and to better identify the cell conditions in the images, leading to better clustering than current methods. In the proposed method, in order to use spatial location data and transcriptomics simultaneously, the samples are modeled using... 

The image-based profile is a technology by which image morphology information is transformed into a multidimensional profile from a set of image-derived features. These profiles can be used to extract biologically meaningful biological information. For example, in the drug discovery process, the mechanism of action of a drug or disease can be identified by examining the morphological properties of the drug in the patient’s cell or tissue and used to design new drugs or use existing drugs for various diseases. High-throughput imaging technology allows the imaging of a large number of different experiments. Extracting valuable features and a good representation of features is the main... 

One of the major challenges in artificial intelligence is the presence of imbalanced data. Imbalanced data occurs when the number of samples in some classes is significantly lower than in others. This imbalance can lead to bias in machine learning models, as models tend to learn better and more accurately from classes with more samples. As a result, they may perform poorly when classifying samples from minority classes. This issue becomes particularly important when minority classes play a critical role in sensitive applications such as healthcare or security. In these cases, it is essential to pay close and fair attention to the minority classes to avoid unjust outcomes. In recent years,... 

Due to the overall progress in the processing of imaging tissue cells, the identification and diagnosis of complex diseases using machine learning methods has become very important. Recognizing cell characteristics such as size, shape, and chromatin design is essential in determining cell type, which can be achieved through learning methods such as deep network training. Finding the nucleus or cytoplasm of cells in medical images is a small but significant part of a long process of diagnosing and treating diseases. Today, artificial intelligence has rushed to the aid of experts in this field and has increased the speed and accuracy of experts in finding these cells and their nuclei. This... 

Recent success of Deep Learning models, resulted in their evergrowing application in many fields. However these models usually require huge datasets, which can sometimes be hard to collect. One of the challenges related to medical data, is the Batch Effect; Medical data is usually gathered through multiple experiments. Each experiment might have a slightly different conditions than the other, resulting a shift in the data related to that batch. Batch effects can have more severe impact during testing time, as the shift in the data distribution could be bigger. Many methods have been proposed to reduce or remove the effect of external conditions on data distribution.Deep Learning models have... 

In this study, we aim to learn representations from microscopic cell images that effectively capture the features of drugs affecting the cells, allowing us to identify effective drugs for treating a disease. We employ two parallel learning paths using predictive and generative models. Specifically, we have achieved a predictive model on the RxRx19a dataset that, unlike previous models, is interpretable, optimized, and robust to dras- tic changes in drug properties. Additionally, we have developed the first generative model on this dataset, which not only generates high-quality images but also discovers a meaningful latent space. This latent space divides the representation into relevant... 

In recent years, deep learning models have become one of the most widely used models in the field of artificial intelligence by showing high accuracy in various applications, in some of which the accuracy and correctness of the output of the models are very important, and in case of an error, there will be a possibility of chaotic events. Along with the progress of deep learning models, attacks have also been introduced in this field that severely compromises the security of such models and affects the accuracy and correctness of their output. Data poisoning is an attack on deep learning models wherein the attacker manipulates some data examples and adds these poisoned data to the victim's... 

Domain shift is an inevitable issue when histopathological images are analyzed in a standard laboratory. This is due to the variations in tissue handling, manual procedures for sample preparation, and differences in scanners. This can result in reduced performance of machine learning algorithms trained on images from one laboratory when applied to another. In this framework, the goal of utilizing domain generalization techniques in machine learning is to develop models that perform well in different domains. This research examines various methods of dealing with the domain shift challenges within the context of detecting mitotic cells, and proposes algorithms to improve domain generalization... 

Identifying the type of disease from microscopic images taken from human tissue is considered a challenging task in cases where diagnosis is difficult and ambiguous for specialists. To resolve this ambiguity, pathologists spend a lot of time finding similar images in databases to determine the label of the ambiguous image based on other pathologists’ diagnoses of similar images. Therefore, automatic image retrieval is one of the active research topics in computer vision and medical image analysis. In this regard, various models have been introduced to enable doctors to perform this task in less time. These models work by receiving an image as input and returning the most biologically similar... 

Deep learning methods are rapidly gaining traction for clinical use in digital pathology. Despite the increasing use of graph neural networks for classifying histopathology images, due to the high accuracy of these methods in this field and the introduction of new interpretability methods for these networks, current proposed solutions still face two main issues. First, there is no comprehensive framework for evaluating the effectiveness of interpretability methods for graph networks, particularly for histopathology images. Additionally, applying conventional interpretability methods to these types of networks for pathology images, with consideration of domain-specific knowledge, has been... 

Many machine learning models make confident decisions when encountering out-of-distribution (OOD) data which differ from their training data distribution. However, these models should not make predictions on unfamiliar samples they have not seen before, and rejecting such unknown samples is crucial for deploying trustworthy models in real-world applications. Consequently, OOD detection has garnered significant attention over the past decade. Despite the development of highly accurate methods to address this issue, there has been little focus on their robustness against various factors. One common factor threatening the robustness of these methods is the presence of spurious correlations in... 

One of the essential features of any artificial intelligence system that is safe for use in the real world is the ability to detect and generalize capabilities when encountering data outside the training data distribution. Intuitively, deep generative models that have the capability to explicitly estimate the likelihood function seem to be a suitable solution for detecting out-of-distribution data. However, recent research has shown that these models, when trained unsupervised, may assign higher likelihoods to out-of-distribution data. There is no consensus among various studies on the fundamental cause of this problem, leading to diverse approaches attempting to solve this issue through... 

This research focuses on physics-informed neural networks, which are trained to solve supervised machine learning tasks while adhering to physical laws described by general nonlinear partial differential equations. Previous studies utilized Gaussian process regression to develop functional representations designed for a given linear operator. However, despite the flexibility of Gaussian processes, solving nonlinear problems presents two major limitations: first, authors had to linearize each nonlinear term over time, and second, the Bayesian nature of Gaussian process regression requires specific assumptions that may limit the model’s representational capacity. For these reasons, data-driven... 

Improvements in deep neural networks and their widespread use in research and practical application have raised significant concerns about the robustness of these networks against adversarial examples designed to deceive a deep network in calcu- lating the correct output with a slight change in input. Since this is an essential issue in highly sensitive applications, it is necessary to use a training method that reduces the model’s sensitivity to these changes but still preserves the accuracy. The common method for this goal is training the model with adversarial examples. In other words, adversarial examples are generated during the training, and the model is trained with them. This allows... 

Whole Slide Image (WSI) classification in digital pathology presents significant computational challenges due to the scale and complexity of the data. Traditional approaches often rely heavily on self-supervised learning (SSL), which demands extensive training periods and computational resources. Moreover, performance can suffer from domain shifts when transitioning from natural images to WSIs. We introduce Snuffy, a novel framework designed to address these challenges effectively. Snuffy utilizes a novel sparse transformer utilizing innovative sparse multi-head class-centered random global attention mechanism tailored specifically for pathology. This approach mitigates performance loss... 

Clustered Regularly Interspaced Short Palindromic Repeats, or in short, CRISPR is a relatively new technology that enables geneticists and medical researchers to edit parts of the genome by removing, adding, or altering parts of the DNA. Initially found in the genomes of prokaryotic organisms such as bacteria and archaea, this technology can cure many illnesses such as blindness and cancer. A significant issue for a practical application of CRISPR systems is accurately predicting the single guide RNA (sgRNA) on-target efficacy and off-target sensitivity. While some methods classify these designs, most algorithms are on separate data with different genes and cells. The lack of... 

Deep reinforcement learning has achieved better cumulative rewards than humans in many environments like Atari. One drawback of these methods is their data inefficiency which makes training time-consuming, and in some cases having this amount of data is infeasible. Meta reinforcement learning can use past experiences to enable agents to adapt to new tasks faster and makes neural networks to train in a short amount of time.One of the methods in meta reinforcement learning is inferring tasks which helps exploitation policy to have good performance in new tasks. There’s a need to improve exploration policy as well as exploitation policy by gaining informative transitions about the new task....