Blog Posts

I could have the baddest jungle beats. Why do I not have them yet? Because I have not trained my neural net.

In [483]: # This Python 3 environment comes with many helpful analytics libraries installed # It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python # For example, here’s several helpful packages to load import numpy as np # linear algebra import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv) # Input data files […]

In Machine Learning, the loss function acts as an accuracy metric. The lower the loss, the higher the capability of predicting correctly. That is, it is inversely proportional to accuracy.

Credit to Rodolfo Saldanha’s Stock Price Prediction with PyTorch. I just changed this from Amazon to Tesla. In [2]: # This Python 3 environment comes with many helpful analytics libraries installed # It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python # For example, here’s several helpful packages to load import numpy as np # linear […]

Music videos tell a story through art. Whether it is the lyrics themselves or the visual imagery, humans can connect with music videos emotionally. First Principles Problem A music video is a sequence of frames synchronized to some minutes and seconds of audio. Assuming a music video could be instantly created by a nerual net, […]

Certainly! Here are ten examples of underserved business plans that could benefit from a path of disruption through continuous engineering improvements: Affordable renewable energy solutions for developing countries Sustainable and eco-friendly packaging for food and consumer goods Autonomous vehicles for public transportation and ride-sharing services Low-cost and sustainable housing solutions for low-income families Electric and […]

There once was a baby raccoon who loved snuggling his mommy. His name was Racarslin.

Building makemore Part 3 Jupyter Notebook makemore: part 3¶ Recurring Neural Networks RNNs are not as easily optimizable with first order gradient techniques we have available to us and the key to understanding why they are not optimizable easily is to understand the activations and their gradients and how they behave during training. In [2]: import […]

Currently it costs in the USA ~ $684/mo to drive 1000 miles with FSD subscription, insurance and energy costs. This works out to $0.684(0.69)/mile. How odd. Most cars sit around doing not that much, most of the time. As you decrease the number $684, you broaden the available market. Even starting with a couple buying […]