Explore the concept of strided convolutions in neural networks.
I work as a Machine Learning Engineer at DeepLab. My goal is to leverage data and AI to improve people’s lives. To that end, I implement machine learning models for biomedical and neural engineering applications. My experience also includes domains like computer vision and natural language processing.
Here's what I've written (so far):
Baeldung on Computer Science
- Machine Learning (18)
- Deep Learning (16)
- Computer Vision (14)
- Math and Logic (4)
- Algorithms (4)
- Artificial Intelligence (3)
Explore face recognition and its importance in today’s machine-learning era.
Learn about landmark detection.
Learn about the algorithm of neural style transfer.
Learn more about end-to-end deep learning method.
Learn about the triplet loss function.
Learn about the method of eigenfaces.
Learn about Recurrent Neural Networks (RNNs).
Explore cosine similarity and its applications.
Learn about gradient-based algorithms in optimization.
Explore the concept of Inception Networks.
Learn about the Residual Networks.
Learn about the global and local optima.
Learn about mathematical optimization.
Learn about how the blur operation works in images.
Explore the Spatial Pyramid Pooling (SPP) layer.
Explore three popular datasets in computer vision.
Explore three ways of using large images as input to CNNs.
Learn about the weight decay loss.
Explore the Conv and the FC layer of a neural network.
Learn about the Scale-Invariant Feature Transform (SIFT).
Learn about the term ablation study in the field of machine learning
Explore the differences between an epoch, a batch, and a mini-batch.
Explore the differences between k-fold leave-one-out cross-validation techniques.
Explore three common methods for computing the similarity between colors.
Learn about a method that converts a color from HSL to RGB.
Learn about the mAP metric for object detection.
Learn about the hidden layers in a neural network.
Learn about self-supervised learning.
Learn about the latent space in deep learning.
Explore two activation functions, the tanh and the sigmoid.
Learn about contrastive learning.
Explore three algorithms for image comparison
Learn about occlusions in image processing.
Learn how to convert an RGB image to grayscale.
Learn about various applications of generative models.
Learn about computing the outputs size of a convolutional layer.
Learn about curve fitting and the least-squares algorithm.
Learn about Generative Adversarial Networks (GANs).
Explore how we can use GANs for data augmentation.
Learn about three key components of a Machine Learning (ML) model: Features, Parameters, and Classes.
Take a look at two of the most well-known classifiers, Naive Bayes and Decision Trees.