Learn what it means when we say that random variables are independent and identically distributed and why this isn’t always easy to check.
Currently, I'm pursuing my Master's Degree at the University of Debrecen. In my field of research in Machine Learning, I'm interested in Generalization Theory, Hyperparameters Analysis, and the influence of synthetic data in training neural networks for Computer Vision applications. Moreover, I'm always trying to expand my knowledge in AI and Computer Science topics.
Here's what I've written (so far):
Baeldung on Computer Science
- Machine Learning (10)
- Deep Learning (5)
- Computer Vision (3)
- Programming (2)
- Math and Logic (2)
- Data Science (1)
Learn about the open-source movement.
Explore the relevance of and how to compute an SVD of a matrix.
Learn the difference between correlation and regression, two statistical techniques we use to analyze the relationship between variables.
Learn about the No Free Lunch Theorem.
Explore the differences between computer vision and image processing.
Learn what image histograms are and when to use them.
Explore semantic and instance segmentation.
Explore data augmentation techniques.
Learn about fine-tuning neural networks.
Learn the differences between backpropagation and feedforward neural networks.
Explore some real-life examples of supervised and unsupervised learning.
Learn how to implement a dynamic programming algorithm to find the optimal policy of an RL problem, namely the value iteration strategy.
Explore different strategies to update the weights during the training phase of any machine learning model.
Learn how we can implement the 20 Questions Game using a nonparametric model called a decision tree.
Explore the differences between high-level and low-level languages.
Learn the main differences between using the whole dataset as a batch to update the model and using a mini-batch