Computer Vision is one of the most interesting and my favorite application area for artificial intelligence. A big challenge for image analysis algorithms is fast detection and classification of objects in real time. The problem of detecting objects is much more difficult than the classification that I have discussed many times on my blog. That’s …
Today I would like to present an example of using logistic regression and Keras for the binary classification. I know that this previous sentence does not sound very encouraging 😉 , so maybe let’s start from the basics. We divide machine learning into supervised and unsupervised (and reinforced learning, but let’s skip this now). Supervised …
Preparing your data for machine learning is not a task that most AI professionals miss. Data are of different quality, most often they require very thorough analysis, sometimes manual review, and certainly selection and initial preprocessing. In the case of classification tasks, the division of a dataset into classes may be inappropriate or insufficiently balanced. …
If I had to indicate one algorithm in machine learning that is both very simple and highly effective, then my choice would be the k-nearest neighbors (KNN). What’s more, it’s not only simple and efficient, but it works well in surprisingly many areas of application. In this post I decided to check its effectiveness in …
In the previous three parts of the tutorial, we learned about convolutional networks in detail. We looked at the convolution operation, the convolutional network architecture, and the problem of overfitting. In the classification of the CIFAR-10 dataset we achieved 81% on the test set. To go further we would have to change the architecture of …
Convolutional neural network is one of the most effective neural network architecture in the field of image classification. In the first part of the tutorial, we discussed the convolution operation and built a simple densely connected neural network, which we used to classify CIFAR-10 dataset, achieving accuracy of 47%. In the second part of the …
Convolutional neural network provides one of the best classification results for images. In the previous post, you had the opportunity to learn what a convolution is and how to classify a CIFAR-10 dataset using a simple densly connected neural network. By the way, we have obtained accuracy of 47% on the test set. In the …
Deep neural networks are widely used in image and shape recognition. Examples of applications include face recognition, image analysis in medicine, handwriting classification, and detection of surrounding objects. A special type of neural network that handles image processing extremely well is a convolutional neural network. I have to admit that ConvNet is my favorite deep …
Do you like statistics? There is a high probability 😉 that you don’t. But don’t worry, statistics are not my strong point either. All in all, it’s hard to say why most people shun statistics, but I feel that many statistical issues are not entirely intuitive. Just reach for the gambler’s fallacy or Monty Hall …
One of the first problems faced by AI students is how to build a development environment for machine learning. This is an ungrateful issue because there are many methods and tools available and sometimes you simply don’t know which to choose and where to start. Added to this are the issues of choosing libraries for …