One of the broadest uses of Snowflake is building a data warehouse platform or enhancing the existing data lake. It offers all sorts of services to build an efficient Data warehouse with ETL capability and support for various external data partners. Slowly Changing dimensions are a common database modeling technique used to capture data in a table and show how it changes over time. The slowly changing dimension of the warehouse dimension is said to rarely change. However, when they change, there should be a systematic approach to capturing that change. Examples of SCDs are customer and products information. This project explains how to build a Slowly Changing Dimension (SCD) using Snowflake’s Stream functionality and how to automate the process using Snowflake’s Task functionality.
CRNNs combine both convolutional and recurrent architectures and is widely used in text detection and optical character recognition (OCR). In this project, we are going to use a CRNN architecture to detect text in sample images. The data we are going to use is TRSynth100k from Kaggle. Given an image containing some text, the goal here is to correctly identify the text using the CRNN architecture. We are going to train the model end-to-end from scratch.
In this machine learning project, we will use binary leaf images and extracted features, including shape, margin, and texture to accurately identify plant species using different benchmark classification techniques.
In this project, we will use time-series forecasting to predict the values of a sensor using multiple dependent variables. A variety of machine learning models are applied in this task of time series forecasting. We will see a comparison between the LSTM, ARIMA and Regression models. Classical forecasting methods like ARIMA are still popular and powerful but they lack the overall generalizability that memory-based models like LSTM offer. Every model has its own advantages and disadvantages and that will be discussed. The main objective of this article is to lead you through building a working LSTM model and it's different variants such as Vanilla, Stacked, Bidirectional, etc. There will be special focus on customized data preparation for LSTM.