Our research is devoted to answering whether randomisation-based learning can be fully competitive with the classical feedforward neural networks trained using backpropagation algorithm for classification and regression tasks. We chose extreme learning as an example of randomisation-based networks. The models were evaluated in reference to training time and achieved efficiency. We conducted an extensive comparison of these two methods for various tasks in two scenarios: $$\bullet$$∙ using comparable network capacity and $$\bullet$$∙ using network architectures tuned for each model. The comparison was conducted on multiple datasets from public repositories and some artificial datasets created for this research. Overall, the experiments covered more than 50 datasets. Suitable statistical tests supported the results. They confirm that for relatively small datasets, extreme learning machines (ELM) are better than networks trained by the backpropagation algorithm. But for demanding image datasets, like ImageNet, ELM is not competitive to modern networks trained by backpropagation; therefore, in order to properly address current practical needs in pattern recognition entirely, ELM needs further development. Based on our experience, we postulate to develop smart algorithms for the inverse matrix calculation, so that determining weights for challenging datasets becomes feasible and memory efficient. There is a need to create specific mechanisms to avoid keeping the whole dataset in memory to compute weights. These are the most problematic elements in ELM processing, establishing the main obstacle in the widespread ELM application.

This article proposes a novel concept for a two-step Ki-67/lymphocytes classification cell detection pipeline on Ki-67 stained histopathological slides utilizing commonly available and undedicated, in terms of the medical problem considered, deep learning models. Models used vary in implementation, complexity, and applications, allowing for the use of a dedicated architecture depending on the physician’s needs. Moreover, generic models’ performance was compared with the problem-dedicated one. Experiments highlight that with relatively small training datasets, commonly used architectures for instance segmentation and object detection are competitive with a dedicated model. To ensure generalization and minimize biased sampling, experiments were performed on data derived from two unrelated histopathology laboratories.

The paper presents two neural based controllers for the computer car racing game. The controllers represent two generations of neural networks—a multilayer perceptron and a spiking neural network. They are trained by an evolutionary algorithm. Efficiency of both approaches is experimentally tested and statistically analyzed.

The paper presents a complete solution for recognition of textual and graphic structures in various types of documents acquired from the Internet. In the proposed approach, the document structure recognition problem is divided into sub-problems. The first one is localizing logical structure elements within the document. The second one is recognizing segmented logical structure elements. The input to the method is an image of document page, the output is the XML file containing all graphic and textual elements included in the document, preserving the reading order of document blocks. This file contains information about the identity and position of all logical elements in the document image. The paper describes all details of the proposed method and shows the results of the experiments validating its effectiveness. The results of the proposed method for paragraph structure recognition are comparable to the referenced methods which offer segmentation only.