Suppose you are learning to recognize faces. A completely empty system has to be told what parts of images are faces. The more faces the system presents in which it has been told which parts are faces the more likely the system will get it right. It isn’t unlike a spam filter where it needs samples of what are spam and what are not before it can start seeing similarities in random cases without a human to help. Once enough samples are given in which someone tells the system the answers (the training) the system may become faster and better than a human at the same thing (think hundreds of thousands of images). It learns by being told what is right or wrong…it can’t know that without help.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Explainer: What Is Active Learning? | 0 | 256 | January 4, 2023 | |
| I would love to be part of it, where/how to start? | 1 | 1003 | December 19, 2015 | |
| Inference: The Next Step in GPU-Accelerated Deep Learning | 1 | 471 | November 13, 2019 | |
| Building a Benchmark for Human-Level Concept Learning and Reasoning | 1 | 333 | November 23, 2020 | |
| Jetson inference training | 2 | 822 | October 18, 2021 | |
| Build an AI Cat Chaser with Jetson TX1 and Caffe | 2 | 331 | January 23, 2018 | |
| Machine vision without using neural nets | 12 | 481 | April 6, 2025 | |
| Intelligent speed adaptation using Nvidia Jetson Tx2 | 0 | 400 | December 2, 2020 | |
| End-to-End Deep Learning for Self-Driving Cars | 20 | 1679 | January 18, 2022 | |
| How to work properly with Jetson TX1 for general purpose AI/ML projects? | 7 | 2346 | October 18, 2021 |