Back

training

Training is the process of teaching an AI system to recognize patterns, make decisions, and predictions based on input data. During training, the model learns from a dataset that has been carefully prepared with input-output pairs. The model’s internal parameters are adjusted through a process of optimization, often using algorithms like gradient descent, to minimize the error in its predictions. This phase is computationally intensive and requires significant resources, including large amounts of high-quality, annotated data and powerful computing platforms[2][3][7]. Training is an iterative process where the model’s performance is continuously evaluated and improved until it reaches a satisfactory level of accuracy[2][3].

Compare with: inferencing

Citations:

[1] https://research.ibm.com/blog/AI-inference-explained

[2] https://www.performance-intensive-computing.com/objectives/tech-explainer-what-is-ai-training

[3] https://ai.plainenglish.io/deep-learning-training-vs-inference-do-you-know-the-difference-72e136a0a070

[4] https://www.arm.com/glossary/ai-inference

[5] https://mitsloan.mit.edu/ideas-made-to-matter/machine-learning-explained

[6] https://stackoverflow.com/questions/55852777/is-training-inference-terminology-in-deep-learning-any-different-than-train-te

[7] https://blogs.nvidia.com/blog/difference-deep-learning-training-inference-ai/

[8] https://www.techtarget.com/searchenterpriseai/definition/machine-learning-ML

[9] https://stats.stackexchange.com/questions/205253/what-is-the-difference-between-learning-and-inference

[10] https://www.xilinx.com/applications/ai-inference/difference-between-deep-learning-training-and-inference.html