#data science #curve fitting #arps Bulk Arps Curve Fitting on GPU This article proposes a method for significantly faster Arps decline curve fitting on large datasets using TensorFlow on GPUs. It tackles the limitations of traditional approaches, which rely on iterative curve fitting, like SciPy's curve_fit, applied to each data point one at a time. By leveraging TensorFlow's parallel processing
#data science #llms #chatgpt Cost-Efficient Text-to-SQL Chatbot Using ChatGPT LLMs Overview Have you ever wondered how to make data more accessible to other employees in your organization without them having to deal with the headache of SQL queries? We would like to share with you our attempt at solving this problem by making a cost-efficient Text-to-SQL chatbot at Raisa. In
Inductive Clustering For Lower Dimension Input Vectors IntroductionWe often need to expand or generalize the output of clustering algorithms for unseen data points in training without recomputing the clustering. Some clustering algorithms support this by nature, which is called Inductive Clustering. This article will discuss extending the non-inductive clustering algorithms to classify new instances and classify data
#deep learning #data science #time series Time Series Forecasting using Transformers and Ordinal Regression Raisa's Domain and Time Series PredictionOne of the things we do at Raisa is forecasting oil and gas production for all wells in the United States. Forecasting are usually done for the next twelve months based on previous data, which is by definition a time series forecasting problem.With the
#machine learning #data science Introduction to Probabilistic Deep Learning Why Bayesian deep learning?Have you ever tried to learn about Bayesian neural networks but got hit in the face with a barrage of equations? Have you ever implemented a Bayesian neural network without actually understanding why this works? If the answer is yes to any of those questions, then
