Workflow of a machine learning project скачать в хорошем качестве

Workflow of a machine learning project

The video outlines the key steps involved in building a machine learning project. The example used in the video is speech recognition, specifically detecting the keywords "Alexa," "Hey, Google," "Hey, Siri," or "Hello, Baidu." The three key steps involved in building a machine learning project are: 1.Collect data: The first step is to collect data that includes audio clips of people saying "Alexa" or other words. This is used to train the machine learning algorithm. 2.Train the model: The second step is to train the model using the collected data. This involves using a machine learning algorithm to learn an input to output or A to B mapping, where the input is an audio clip and the output is the word that was spoken. 3.Deploy the model: The third step is to deploy the model into an actual smart speaker and ship it to a group of test users or a larger group of users. This step involves iterating and fine-tuning the model to work better and updating it as needed based on feedback from users. 4.The video also provides an example of how these steps can be applied to building a key component of a self-driving car, specifically a machine learning algorithm that takes as input a picture of what's in front of the car and outputs the position of other cars. The first step is to collect data, which includes images and the positions of other cars. The second step is to train the model, which involves fine-tuning the model until it works well. The third step is to deploy the model into a self-driving car and iterate and fine-tune it as needed.