A quick and practical guide to embedding layers in neural networks and their applications.
Enes is a data scientist with over three years of experience, currently working as a freelancer for Toptal. Enes has a strong background in mathematics, computer science, and machine learning and is passionate about learning and exploring any area related to machine learning.
Here's what I've written (so far):
Baeldung on Computer Science
- Machine Learning (12)
- Deep Learning (7)
- Artificial Intelligence (5)
- Math and Logic (4)
- Algorithms (4)
- Computer Vision (2)
- Searching (1)
- Data Science (1)
A quick and practical introduction to Gibbs sampling.
Learn about the concepts of transfer learning and meta-learning.
A quick an practical guide to backbones in neural networks.
A quick and practical guide to finding the closest string matches.
A guide to feature importance in Machine Learning.
A comparison between the Porter and Lancaster stemming algorithms.
Learn about n-grams and some practical applications for them.
A guide to the YOLO algorithm for object detention
Learn how to update the bias term with backpropagation.
A comparison between regular neural networks and convolutional neural networks.
Understand the term “depth” when it comes to convolutional neural networks.
A guide to validating neural networks with K-Fold Cross-Validation.
Understand the differences between bidirectional and unidirectional LSTM.
An overview of the learning rate and batch size neural network hyperparameters
An overview of the word2vec algorithm and the logic behind word embeddings.
Learn about two commonly used machine learning metrics, accuracy and AUC.
Learn about Latent Dirichlet Allocation and the coherence score
Go over an overview of linear regression, and why we need regularization.
A quick and practical comparison between SVM and a perceptron.
Learn the basic concepts behind convolutional neural networks, commonly used in computer vision tasks, and how to construct them.
A quick and practical guide to extracting dates, times, and addresses from any text data.
Explore some important terms relared to time-series forecasting.
A quick and practical explanation of out-of-bag errors in random forests.
Learn about the Grey Wolf Optimization (GWO) algorithm and how it works.