Completed Certifications
DeepLearning.AI Deep Learning Specialization
TensorFlow • CNNs • NLP • Transformers • RNNs
Overview
Completed an advanced series on neural networks in January 2026, covering core deep learning architectures and modern training strategies. The program involved building and optimizing CNNs, RNNs, LSTMs, and Transformers using TensorFlow and Python.
Through hands-on projects spanning image recognition, natural language processing, and neural style transfer, I strengthened my understanding of model optimization, architecture design, and training dynamics, gaining practical experience in implementing and evaluating state-of-the-art deep learning systems.
Skills developed: TensorFlow, Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Sequence Modeling, Natural Language Processing (NLP), Neural Style Transfer, Transformers, HuggingFace, Dropout, Batch Normalization, Hyperparameter Tuning
DeepLearning.AI Machine Learning Specialization
TensorFlow • XGBoost • Neural Networks • Regression • Decision Trees
Overview
Completed in July 2024, this specialization taught by Andrew Ng covers foundational and advanced machine learning techniques with a focus on real-world application. I gained hands-on experience developing and optimizing models using Python and industry-standard libraries.
Key learnings include: supervised learning algorithms (e.g., linear and logistic regression), tree-based models, ensemble techniques like XGBoost, recommender systems, anomaly detection, and core neural network concepts using TensorFlow.
Skills developed: Supervised Learning, Unsupervised Learning, Reinforcement Learning, Gradient Descent, Logistic Regression, Linear Regression, Decision Trees, TensorFlow, XGBoost, Recommender Systems, Collaborative Filtering, Anomaly Detection, Artificial Neural Networks
IBM Data Science Professional Certificate
Python • SQL • Pandas • Scikit-learn • Data Visualization
Overview
Earned in September 2023, this 10-course certificate program provided comprehensive training in the data science lifecycle—from data collection and cleaning to model development and deployment. It emphasized practical applications using real-world datasets, with tools like Pandas, Scikit-learn, SQL, and Matplotlib.
Projects covered exploratory data analysis, predictive modeling, dashboards, and more—enhancing my ability to draw actionable insights from complex data.
Skills developed: Data Analysis, Data Wrangling, Data Visualization, Classification, Regression, Clustering, Recommender Systems, Python, SQL, Pandas, NumPy, Scikit-learn, Seaborn, Matplotlib, GitHub, Jupyter Notebooks, Machine Learning