GANs and diffusion models for Simpsons and MNIST generation.

Study that evaluates two CNN architectures for the Simpsons classification problem: Model 1 with 4 convolutional blocks and 1024 neurons, and Model 2, a simplified Xception model, emphasizing edge detection for well-defined images.

Making use of Recurrent Neural Networks (RNNs), the aim was to create a new Simpson’s TV script at Moe’s Tavern. I’ve used a part of Simpson’s dataset of scripts from 27 seasons.

Scraping The Simpsons Transcripts with R

Here I have written a model and a pre-trained model for a classification task.

WWI19A project - Recognising images of popular Simpsons characters using a Convolutional Neural Network

DCGAN image generator 🖼️.

📁 A small MNIST-like The Simpsons character database to at least have some fun while training neural networks.

Training a model to classify the simpsons character on the image using model from canaro, dataset with simpsons characters from kaggle.

Both the slides and demos of my session "Deep learning from zero to hero" (in italian language) at AI&ML Conference 2019

DCGAN Simpsons Faces Image Generator usging Tensorflow2 Alpha 🖼️.

Udacity TV Script Generation Project

This RNN learns and writes Simpsons scripts (P3 - DLND)

Simpsons Characters object detection using tensoflow object detection api

Various implementations and projects on CNN, RNN, LSTM, GAN, etc

Use of RNNs to build a TV script using 'Simpsons by the data' dataset from Kaggle