Welcome to my data science portfolio! This portfolio showcases some of my projects and work related to data science, machine learning, and artificial intelligence. Each project includes a brief description, the data used, and the techniques and tools applied.
(Capstone project for M.I.T. Applied Data Science Program)
The goal of this project is to use Deep Learning and Artificial Intelligence techniques to create a computer vision model that can accurately detect facial emotions.
I have been given about 15,000 48x48 images of:
● Images of people who have happy facial expressions.
● Images of people with sad or upset facial expressions.
● Images of people who have shocked or surprised facial expressions.
● Images of people showing no prominent emotion in their facial expression at all.
Python, numpy, pandas, matplotlib, Tensorflow, Keras, Data Augmentation, Convolutional Neural Networks, Computer Vision
Kaggle Playground Series Season 3, Episode 2: Tabular Classification with a Stroke Prediction Dataset
(Stroke Occurrence Prediction)
Build a classification model using neural networks to predict the probability of a stroke based on demographic data
The dataset for this competition (both train and test) was generated from a deep learning model trained on the Stroke Prediction Dataset. Feature distributions are close to, but not exactly the same, as the original.
Python, numpy, pandas, matplotlib, seaborn, scikit-learn, Tensorflow, Keras, Feedforward Neural Networks, Convolutional Neural Networks
(Kaggle's first ever unsupervised clustering challenge)
In this challenge, you are given a dataset where each row belongs to a particular cluster. Your job is to predict the cluster each row belongs to. You are not given any training data, and you are not told how many clusters are found in the ground truth labels.
For this challenge, you are given (simulated) manufacturing control data that can be clustered into different control states. Your task is to cluster the data into these control states. You are not given any training data, and you are not told how many possible control states there are. This is a completely unsupervised problem, one you might encounter in a real-world setting.
Python, numpy, pandas, matplotlib, scikit-learn, Tensorflow, Keras, Clustering: K-means and GMM, Dimensionality Reduction: PCA, Autoencoder
More to come!
-
Python
- Numpy
- Pandas
- Tensorflow
- Keras
- Matplotlib
- Scikit-learn
- Seaborn
-
Data Science
- Machine Learning
- Deep Learning
-
R
-
Java
-
C
-
SQL
-
Probability
-
Statistics
-
Mathematics
B.A. in Mathematics and Biochemistry from Lewis & Clark College
Certificate in Applied Data Science from Massachusetts Institute of Technology
Business Systems Engineer at Onsight Services, LLC: April 2022 - Present
Math and Science Tutor: January 2019 - Present
Contact
Email: [email protected]
Additional Resources
LinkedIn: https://www.linkedin.com/in/benjaminrschulman
Linktree: https://linktr.ee/bschulman
Thank you for visiting my portfolio, I hope you find it informative. If you have any questions or would like to discuss any of my projects, please don't hesitate to contact me.
Disclaimer
Please note that the data used in these projects is for educational and demonstration purposes only. The analysis and conclusions drawn from the data are not intended to be taken as fact.