- Machine Learning & Deep Learning (CNNs, transfer learning model)
- Artificial Intelligence research and real-world applications (eg, Kannada-MNIST, plant disease detection)
- Data Science & Analysis (EDA, preprocessing, feature extraction)
- Curiosity-driven learning, and problem-solving
Achyutha Jagadeesh
Tumkuru
Summary
Aspiring Machine Learning and Deep Learning enthusiast with strong skills in Python, TensorFlow, Keras, scikit-learn, NumPy, and Pandas. Experience in building and evaluating ML/DL models including CNNs, RNNs, and transfer learning architectures (VGG16, DenseNet, GoogLeNet, EfficientNet). Proficient in data preprocessing, feature extraction, and model evaluation with metrics such as MSE, MAE, RMSE, and Accuracy. Hands-on experience in full-stack web development (MERN stack) and academic research involving literature surveys, comparative analysis, and real-world applications like plant disease detection and Kannada-MNIST classification. Strong analytical thinker with a curiosity-driven mindset.
Overview
1
1
Certification
Work History
Recognition of Hand Written Digits Using MNSIT
- Implemented handwritten digit recognition using the MNIST dataset (70,000 grayscale images of size 28×28).
- Built a Convolutional Neural Network (CNN) to automatically learn spatial features through convolution, pooling, and fully connected layers.
- Trained the model to classify digits (0–9) with high accuracy.
- Achieved over 99% accuracy on the test set, showcasing the effectiveness of CNNs in image classification tasks.
- Mucked out, cleaned and sanitized animal stalls and barn area.
Website Summarizer Using OpenAI API
- Built a tool to extract text from webpages and generate concise summaries using a language model (GPT-4o via OpenAI API).
- Implemented a workflow involving content fetching, cleaning, and splitting long text into smaller chunks for efficient processing.
- Summarized individual chunks and combined them into a final structured output.
- Generated results including a TL;DR, key points, important facts/quotes, and source references, enabling users to quickly understand lengthy articles or reports.
Survival Prediction on Titanic Dataset
- Predicted passenger survival on the Titanic using machine learning techniques.
- Performed data exploration and preprocessing, including handling missing values, feature engineering (e.g., FamilySize, Title), and categorical encoding.
- Selected Gradient Boosting Classifier as the primary model for prediction.
- Applied hyperparameter tuning and evaluation to optimize performance.
- Achieved 85% accuracy on the test set, demonstrating strong predictive capability.
Education
Bachelor of Engineering - Information Science
R N S Institute of Technology
Bengaluru01-2026
Skills
- Proficient in Python
- NumPy
- Pandas
- Scikit-Learn
- TensorFlow / Keras
- Matplotlib
- PyTorch
- EDA
- Debugging and troubleshooting
- Excel
- Power BI
- SQL/No SQL
Interests
Certification
- Data Science Job Simulation, Commonwealth Bank - August 2025
Languages
English
Upper intermediate (B2)
Hindi
Intermediate (B1)
Kannada
Upper intermediate (B2)
Japanese
Elementary (A2)
Timeline
Recognition of Hand Written Digits Using MNSIT
Website Summarizer Using OpenAI API
Survival Prediction on Titanic Dataset
Bachelor of Engineering - Information Science
R N S Institute of Technology
Similar Profiles
Adrián Pópulo QuirogaAdrián Pópulo Quiroga
Canguro at NACanguro at NA
Savanna FosterSavanna Foster
Personal Babysitter at NAPersonal Babysitter at NA
Elizabeth Paige SessomsElizabeth Paige Sessoms
Stay-at-Home Parent at NAStay-at-Home Parent at NA
Cathy Mih TaylorCathy Mih Taylor
NA at NANA at NA
Ashwini NAshwini N
Intern at Sri Annapurneshwari IndustriesIntern at Sri Annapurneshwari Industries