Archived
Let’s imagine one wants to create two algorithms which both aim at answering the following question: is there a car on the picture?
One of them would be based on machine learning whereas the second one would be based on deep learning. How would the car features be learned by each of he programs? (features = significant elements that enable the computer to recognize them)
0
Community EvaluationsNo one has reviewed this question yet, be the first!
Similar QuestionsMore questions about Machine Learning
9
How to handle missing data in a given training data set ?6
How to handle missing data in a given training data set ?5
What is the missing word in the following sentence: Overfitting is the production of a model that corresponds too closely to the training data set and may therefore fail to fit other data sets and so fail to perform any reliable forecast.4
The validation set is used to provide frequent and unbiased evaluations of the model’s fit on the training set while tuning its hyperparameters/parameters: in other words,the model is found and then tested on the validation set before to be improved once again.4
Clustering is an unsupervised machine learning process which aims at automatically discovering natural grouping in the input data. When using this method, the developer is able to choose the number of groups he wants to create.