Updated the website

index.html

@@ -91,11 +91,15 @@ <h2 class="h1">Akshatha Mohan</h2>
     <div class="about-section">
         <h2 class="h2 fw-light mb-4">About Me</h2>
         <p class="intro">
-          <span class="wave">👋</span> Welcome to my professional corner on the web! 
-          <p>I am a passionate machine learning engineer dedicated to crafting efficient AI systems that drive predictive automation. With a solid foundation in statistics and programming, I excel at navigating complex datasets to develop and optimize machine learning models. My collaborative approach spans across teams—from data scientists to engineers—ensuring scalable solutions that meet rigorous production standards.</p>
+           <p> I am a Computer Engineering graduate student at Texas A&M University, specializing in Machine Learning and 
+            Computer Vision. My passion lies in applying cutting-edge AI techniques to solve real-world problems, particularly in the realms of remote sensing and biomedical imaging. As a Machine Learning Researcher at Texas A&M's Advanced Vision and Learning Lab, I've been at the forefront of pioneering 
+            Explainable AI (XAI) methods for remote sensing applications. My work has significantly boosted the interpretability of complex ML models, increasing decision-making efficacy in remote sensing by 66%. I've also developed efficient PyTorch data preprocessing pipelines for satellite datasets, achieving 95% model accuracy.</p>
+
+           <p> Currently, my research focuses on texture analysis in biomedical imaging, particularly examining lung cells and SEM images. I'm working on an innovative approach to differentiate between cells exposed to various chemicals and untreated cells. This involves generating lacunarity feature maps and calculating Earth Mover's Distance (EMD) loss to quantify the differences. This work builds upon my previous research on lacunarity pooling layers for plant image classification, which has been accepted at the 2024 
+            IEEE/CVF Computer Vision and Pattern Recognition (CVPR) conference. Throughout my projects, I've leveraged cloud technologies, including AWS services like SageMaker, Bedrock, S3, and EC2, as well as Azure platforms such as 
+            Data Factory and Databricks. This experience with cloud computing has enabled me to develop scalable and efficient solutions for complex machine learning tasks.</p>
 
-          <p>At Texas A&M's Advanced Vision and Learning Lab, I specialize in leveraging cutting-edge frameworks like PyTorch and TensorFlow to enhance machine learning pipelines. My projects include interpreting ML models using Explainable AI methods and metrics in models such as ConvNeXt and Vision Transformers. I am adept at implementing MLOps workflows on platforms like AWS Sagemaker and Azure AI Fundamentals, facilitating seamless and automated model deployment. These experiences have honed my ability to collaborate effectively across interdisciplinary teams, delivering impactful solutions in predictive automation.</p>
-          <p>During my Master's thesis, I pioneered a novel pooling layer that integrates lacunarity-based features with pre-trained ones to enhance neural network feature extraction across diverse image types. This innovation significantly improves spatial information capture, achieving superior performance compared to traditional methods and notably boosting classification accuracy. Moreover, my research dedication led to three publications in IEEE and at CVPR, showcasing my commitment to pushing the boundaries of computer vision and machine learning.</p>        </p>
+
     </div>