Understanding how to choose activation function in the final layer and loss function for neural network — Machine learning models consist of mathematical processes that follow a certain flow adaptation. This requires a certain harmony and balance. While the model is being built, the process from importing the data to evaluating the results can take place with tons of different combinations. So, machine learning, especially deep learning…

Implementing configured U-Net architecture from scratch in python and semantic segmentation of the aerial imagery captured by a drone using different approaches — In machine learning, models are trained with various applications, especially on deep learning and image datasets. With the methods based on convolutional operation, many studies are carried out in many fields, especially hand-arm detection in Augmented Reality, self-driving cars, aerial images with drones, war technologies. The human eye has the…

Exploratory Data Analysis of last 5 years’ Power Consumption and Predicting the future Power Consumption using LSTM(RNN) and DNN — Human beings live on the time axis and design their daily life accordingly. Mostly they sleep at night and other activities are mostly done at certain times (e.g. breakfast — in the morning). When we consider language, it is known that what is spoken or written maintains and follows certain…

Exploring Poisson distribution and predicting Galatasaray vs Fenerbahce match result using it with python implementation — Understanding the dataset, performing appropriate preprocessing operations, and interpreting the results are essential for training the machine in the light of more accurate data. For example, if we consider dimensionality reduction, the type of dimensionality reduction method (linear or nonlinear) is applied depending on the structure of the dataset. Distribution…

Explaining and interpretation of isometric feature mapping — Dimensionality reduction methods visualize the dataset and reduce its size, as well as reveal different features in the dataset. For non-linear datasets, dimensionality reduction can be examined under various sub-titles such as distance preservation (Isomap), topology preservation (Locally Linear Embedding). This article explains the theoretical part of isometric feature mapping…

The mathematical proof in the light of behavioral science that building new roads is not a solution to traffic jams — Dietrick Braess, a German mathematician, has noticed something interesting in 1968. Normally, when a new road is built, we expect traffic flow to be faster, but in some cases, building a new road worsens traffic congestion, based on his calculations. Building a new road at some key points does not…

Explaining and reproducing Multidimensional Scaling (MDS) using different distance approaches with python implementation — Dimensionality reduction methods allow examining the dataset in another axis according to the relationship between various parameters such as correlation, distance, variance in datasets with many features. After this stage, operations such as classification are performed on the dataset with supervised or unsupervised learning methods easily. In addition, if we…

Applying Ensemble Learning Algorithms to the image dataset that are features extracted by Convolutional Layers with a python implementation — Table of Contents 1. Introduction 2. Layers 2.1. Convolutional Layer 2.2. Pooling Layer 2.3. Dropout Layer 2.4. Flatten Layer 3. Tutorial 3.1. Dense Layer Approach 3.2. Ensemble Learning Approach 4. Results 5. Discussion 1. Introduction It is mostly converted into (n_samples, n_features) and the algorithm is applied, after the necessary data preprocessing…

Chrome extensions that make life easier and you can get for free — While preparing a project or researching something on the internet, many things that can be defined as drudgery take more time than necessary and distract. Some of the difficulties experienced by almost everyone, such as taking screenshots, getting lost in tabs, switching between devices are easy to do but can…