Reinforcement Learning - Lunar Lander with DQN
Teaching a Neural Network to Land on the Moon I wanted to see how far a small neural network could get at a classic control problem with no rules written by hand. The task: land a spacecraft gently on
Doc Zamora's ML & AI
Latest articles
Custom Annotation for Roboflow Pre-trained Models with CV2
Roboflow has a great playground of models for computer vision, including object detection and tracking. Their web interface allows you to create datasets and labeling tools that can help any team label faster and be more collaborative with their onli...
Audio Transcription from HuggingFace Pre-Trained Model
One time, somebody asked me if it was possible to transcribe call center conversations to text so they later be analyzed for quality purposes. This is exactly what we will be trying to do here in the most simple way: audio transcription. Fortunately,...
Gaussian Mixture Models (GMMs)
Male and Female Weight Let's suppose we collected some data from some University students. We asked every student their gender (Male = M, Female = F) and their weight. We will build a model that can predict if you are a male or a female based only on...
Super Hero Search Made-Easy with OpenAI GPT-3 Models
using text-embedding-ada-002 for search based on similarity
Online Love: Distance-based Couple Matching with Quota
Introduction Greetings, friends; in this post, I will explain my solution for a variation of the Stable Matching problem, particularly for the case of couple matching. The idea is that given a set of Men (M) with, let's say, ten dudes and a set of Wo...
Content-based Recommender System for Movies with Tensorflow
Low-level use of TensorFlow to recommend unseen movies to users.