The Earth layer is where your files and datasets take root. Explore your garden of information, and discover how your contributions have nurtured the growth of understanding within the community.
Description | ||||||
---|---|---|---|---|---|---|
SpaceX rocket launch trail caught in Southern California | From the launch on June 18, 2024. Captured in Carlsbad, CA. | image/jpeg | Public | |||
oil-price-forecast-july-2024 | Forecasted oil prices (WTI Crude) for July 2024 | Dataset | Public | |||
AI models can be built that take one medium of input and return a modifed creation of the same medium | Image-to-image, audio-to-audio, video-to-video, and text-to-text are all examples of different possible input-output mediums AI models can be created to support | image/png | Public | |||
A sketch is elevated in detail and style by a AI model | The human sets the intention, style, and pose in their initial sketch. Through prompting, they are able to elevate their creation by changing the material, lighting, scene, or through any other creative freedom. | image/png | Public | |||
autots-metric-weighting-comparison-rmse | Forecast generated by AutoTS with an increase RMSE metric weighting and a decreased sMAPE weighting. | Dataset | Public | |||
autots-metric-weighting-comparison-made | Forecast generated by AutoTS with an increase MADE metric weighting. | Dataset | Public | |||
autots-metric-weighting-comparison-mle | Forecast generated by AutoTS with an increase MLE metric weighting. | Dataset | Public | |||
autots-metric-weighting-comparison-balanced | Forecast generated by AutoTS with the default, balanced metric weighting. | Dataset | Public | |||
Ouro Devlog 2 | This is Ouro Devlog #2. In this episode we talk about the newly added Teams functionality, built to organize people around common topics and align intent when creating and discovering content. We also talk about how our GTM strategy has shifted as we look to onboard AI API companies and what we learned that led us to adopt this strategy. | video/mp4 | Public | |||
Product demand forecast optimized on sMAPE | If the demand is too random, there is sometimes nothing better than a flat line of zeroes, or ones. However, most clients/stakeholders do not like flat lines for forecasts. | image/png | Public | |||
Product demand forecast optimized with the Wasserstein metric | The Wasserstein or Earth Moving Metric looks at how much energy is required to reshape the predicted forecast into the actual data. For a lot of demand forecasting use cases, like inventory management, being close, say within a day, is usually pretty good and within the tolerances of the system, making Wasserstein distance a good choice. | image/png | Public | |||
Pros and cons of different forecasting approaches | Statistical, machine learning, and deep learning forecasting approaches each have their own unique pros and cons | image/png | Public | |||
Profiling time series allows you to categorize your data into understandable buckets | Nousot's demand forecasting solution splits your data into four major buckets in order to model each one separately. | image/png | Public | |||
Demand forecasting solutions are plauged by three common problems | They are challenging to model, difficult to scale, and painful to integrate. Credit https://www.nousot.com/resources/using-genai-to-completely-disrupt-traditional-platform-migrations-to-databricks-2/ | image/png | Public | |||
Regime identification for SP500 realized volatility | Significant deviations in attention patterns can be observed around periods of high volatility –corresponding to the peaks observed in dist(t). Credit https://arxiv.org/pdf/1912.09363 | image/png | Public | |||
One word with multiple meanings | How would a computer know that the word “bank” in the first sentence refers to a setting in nature, and in the second sentence to a financial setting? The way you and I did it was probably to look at the neighboring words. Credit https://docs.cohere.com/ | image/png | Public | |||
Early alchemical ouroboros illustration | Ouroboros illustration with the words ἓν τὸ πᾶν ("The All is One") from the work of Cleopatra the Alchemist in MS Marciana gr. Z. 299. (10th century) | image/png | Public | |||
A simple sine wave time series | This time series has a single dynamic that can be learned by a local model which only looks at the historic data to make future predictions. | image/png | Public | |||
Training data determines the prediction in a global model | In this sketched example, we have two training time series examples where there is a a hump immediately followed by another hump of varying size. The predicted data follows this same pattern. | image/png | Public | |||
Ouro Devlog 1 Part 2 | This is part 2 of the first Ouro Devlog. We take a quick look at the new service added from StabilityAI and use on of their image-to-image control routes. | video/mp4 | Public |
Rows per page