| Popis: |
Everyday computers can be used to solve numerous tasks which are often too difficult for humans to do quickly. Whether it is finding the shortest route between your home and your work or automatically finding the solutions to puzzles such as sudoku’s, computers can solve these problems faster and often better than humans can. On the other hand, there are problems that are easy for humans, but much harder for computers to do automatically, such as face identification or pattern recognition in images. The state-of-the-art technique for solving these problems is machine learning. Different types of machine learning exist, most of them boiling down to supplying data to a computer, which then learns to produce a required outcome. The more data is given, the closer the outcome will be to the actual solution or the higher the probability will be that the correct solution is found. |
