Pinned Repositories
AudioFiltering-FFT-DopplerShifts
cs5324-MachineLearningNotebooks
Heartbeat-Reading-and-Face-Detection
Using Core Image and OpenCV in iOS to detect faces and read heartbeats of a user with the iPhone's built-in flashlight.
Loan-Default-Deep-Dive-EDA
Dove deep into the context of a dataset from Kaggle containing extensive information (around 36 features) on around 150,000 loan applicants.
MRI-Tumor-Detection-with-ResNet50-and-DinoV2
Performed PCA and Randomized PCA, Fine-tuned ResNet50 to achieve a 94% accuracy in identifying tumor type in MRI images, and showcased human-interpretable feature reduction and mapping with Meta's DinoV2 model.
Saxophone-Hero
Step onto the stage with Saxophone Hero, where your tenor saxophone is the key to unlocking a rhythmic adventure through a world of sheet music. In this game, your character scores points by hitting the right notes. Powered by machine learning, the game captures the pitch from your saxophone and translates it to player movement in real time.
Search-Engine-in-Cpp-With-Custom-HashMap-Implementation
Coded a Search Engine in C++ by reading in JSON files and storing relevant data in custom HashTable data structures. Ranked #1 for overall search speed out of ~100 competitors.
Solving-2D-Poissons-Equation-Using-Finite-Difference-Method-and-Iterative-Solvers
Implementing 2D Poisson's Equation using the Finite Difference Method and Iterative Solvers for matrices. Explored LU decomposition & the Thomas algorithm, Jacobi, Gauss-Seidel, and the Standard Over-Relaxation (SOR) method. MATH 4315: Advanced Scientific Computing with Professor Weihua Geng.
Stock-Price-Prediction-Using-Historical-Data-and-Recurrent-Neural-Networks
Predicted Target (NYSE: TGT) stocks by implementing a variety of models with Recurrent Neural Networks (RNNs) using TensorFlow. Utilized a variety of predictors that I believed provided valuable insights.
Twitter-Sentiment-Analysis-in-Cpp-vs-Python
I implemented a Logistic Regression model in C++ and Python to classify whether or not a tweet has a positive or negative sentiment associated with it. My C++ code involves training Logistic Regression from scratch, while my Python code includes visualizations to better understand the process.
reece-iriye's Repositories
reece-iriye/Twitter-Sentiment-Analysis-in-Cpp-vs-Python
I implemented a Logistic Regression model in C++ and Python to classify whether or not a tweet has a positive or negative sentiment associated with it. My C++ code involves training Logistic Regression from scratch, while my Python code includes visualizations to better understand the process.
reece-iriye/Stock-Price-Prediction-Using-Historical-Data-and-Recurrent-Neural-Networks
Predicted Target (NYSE: TGT) stocks by implementing a variety of models with Recurrent Neural Networks (RNNs) using TensorFlow. Utilized a variety of predictors that I believed provided valuable insights.
reece-iriye/Exploring-Errors-in-Regression
Explored Machine Learning regression models of varying flexibility and how flexibility relates to MSE, Bias, and Variance in our predictions for MATH 4377: Math of Machine Learning. Visualizations of the Bias-Variance trade-off are included, and the project heavily relied on Spline Regression degrees of freedom for flexibility measuring.
reece-iriye/QR-Decomposition-via-Householder-Reflectors-and-Gram-Schmidt
Coded QR and QL Decomposition functions using Householder reflectors and Gram-Schmidt for MATH 6316: Numerical Linear Algebra @ SMU.