machine learning - Evan Marie Carr

🔭 PROPHET: the good & the meh

Prophet, formerly known as fbprophet, is a time series prediction machine learning model that is praised for ease of use, functionality, and performance. I have seen it drastically outperform ARIMA and SARIMAX models, and so I decided to put it to the test with some challenging data. What I found

time series

💪 XGBoost Time Series Prediction

In the world of time series prediction, often LSTM models, as well as the newer trend toward transformers, are primarily what are thought of as leading edge. But I personally have a great admiration for XGBoost models and the raw power they offer, and there are times when XGBoost can

pytorch

◮ Ethereum Price Prediction with LSTM

The time series aspect of time series data can feel like a bit of a hurdle to jump over, and predicting stock and crypto prices is a whole other time series beast to tame. So in this article, I will walk you through the steps of creating a basic architecture

gans

🎥 Celebrity GAN: Generating Faces Out of Stars

Reformed Opera Singer Takes on GANs:A year ago, I was an opera singer, a voice-teacher, and a songwriter; i.e. many facets of who and what I am would have me labeled the creative type. And I do not think many people realize how much creativity there is in

gans

🌷 My GAN Gave Me Flowers

Not very long ago, I began working with GANs. After about 10 min into my first project, and I was already in love. And for me, it is not about what I can make with it as much as having the visual representation that shows me every epoch along the

neural networks

👩🏻 Regression with Images

Recently, I have been spent a lot of time on the Fast.ai Practical Deep Learning for Coders course, and at the same time I have been delving more deeply into the inner structures and workings of neural networks with Jovian's Deep Learning: Zero to GANs. Experiencing both of these

resnet

Visual / Code Map of Resnet

I put this image together tonight as I was trying to internalize all the things that go on in a Resnet model. I am the kind of person who has to feel like I know something intimately to feel like I KNOW it at all. So this code and I

neural networks

🐩 Teaching a Model 37 Dog and Cat Breeds

I find it hard not to be intimidated when a neural network model can differentiate between dog and cat breeds that I honestly just cannot. But instead, I just get really excited about the possibilities and potential and am just grateful for all the work that so many amazing humans

machine learning

🛳️ The Titanic: Predicting Survival

I have been working A LOT with Fast.ai lately, and I am loving it. I am learning so many new approaches that I feel like get overlooked by many in the field when discussions arise. But I have to admit: I was a little nervous when it came to

neural networks

🐸 CIFAR10 with Fast.ai

I had a project where I was meant to get the highest accuracy possible on this set with PyTorch, no convolution, no pooling, not even a learning rate scheduler, just linear neural networks. Ask me how frustrating that was! The highest I could get was 52%, after HOURS and HOURS

neural networks

🔥 Hot or Not? Beauty in the Eye of the Mainstream

I know it sounds a bit callous, but hear me out. After I made my first three little web apps using fast.ai neural network methods, for classifying cats vs dogs, 3 different types of bears, and 3 human emotions/facial expressions, I watched my children spend literally HOURS playing

deep learning

🐻 Deep Learning Image Recognition: 3 Projects in One

I have been working tirelessly on perfecting my skill at image classification, thanks to my new fascination with fast.ai and the work of Jeremy Howard and his team. Today, I made three...almost four...web apps. I got to know HuggingFace.com quite well, and I honestly have had

fastai

🤯 fast.ai & Dog Breed Image Recognition via Transfer Learning

Deep learning. Transfer learning. Mind-blowing! How is fast.ai not EVERYWHERE?! I have been working with neural networks for a little while now. When I was introduced to the practice, I fell in love immediately. So I have been immersing myself all day every day, completing and compiling my own

neural network

🧠 Neural Network Image Recognition

Jupyter - PDF I dance with neural networks. It might sound odd to you, or silly even. But I do. Training a deep learning neural network is a dance. And to anyone who has never danced that dance, all I can do is try to describe it. I will make

neural network

% PyTorch Neural Network: a Look at Life Expectancy with 95.86% Prediction Accuracy

COMPLETE NOTEBOOK - PDF ➥ INTRODUCTION:This notebook is a journey with PyTorch's neural network technology and a custom class linear regression model with the objective, or destination of this journey, of predicting life expectancy as accurately as possible using the quite thorough dataset from the World Health Organization with comprehensive

deep learning

🔥 PyTorch: It's Python on FIRE! 🔥

PyTorch is an open source machine learning library that works directly with Python that to make neural network modeling quick and painless. As soon as I met PyTorch, I knew immediately that it was going to join the collection of my absolute most favorite libraries, along with NumPy, Pandas, and

nlp

🧠 NLP and TensorFlow: Text Prediction and Generation

I spent a great deal of time in the last couple of days diving more deeply into deep learning. And I LOVE it! The possibilities are only as limited as my own imagination, and therefore, they are truly infinite. Well, they are as infinite as my ability to stay awake.

covid

🦠 Long-Covid Data Investigation

* Disclaimer: I am not now, nor have I ever been an anti-vaxxer. This is a story, through real data, of my family's struggle with long-covid and the drastic and mysterious reaction my husband's body has had to both the covid virus as well as the vaccine. I am vaccinated and

data science

🚕 NYC Taxi Prediction: 1.5 million+ rows of data 🫣

This was the most intense project I have completed thus far. And I guess that would be appropriate! It is my final for my current course, Machine Learning: Zero to GBMs at Jovian.ml.

codng

👩🏻‍💻 A day of dynamic programming...OH MY!

Well, THAT was a day! It started out with me saying that I was not going to continue my Linked In Learning subscription, because after going through 4-5 courses and getting certificates and skills on my profile, I found that I was unimpressed with the courses I perused and considered.

australia

🇦🇺 Australian Rainfall Prediction

It is amazing how many hours one can spend with data and get...well...50 cells along in an ENTIRE day! But I did learn a lot about what one CAN and canNOT do to sweet talk decision trees and random forest models. I tried and tried to get data

plotly

📊 Plotly: the great and the disappointing

(Jupyter Notebook link for this project) I was a BUSY girl today! I just spent an entire Sunday, as in a whole 10 and a half hours, learning the ins and outs of Plotly and some very cool dynamic data visualization. I also ran into some GIGANTIC road blocks in