Technical Fridays | Blog
Personal notes on machine learning, deep learning, and software engineering — what's Technical Fridays?
- Personal
- Data Science
- Machine Learning
- R
- Python
- Algorithms
- Cryptography
- Mathematics
- Visualization
- Deep Learning
- Computer Vision
- Natural Language Processing
- Generative AI
- Speech Recognition
- PyTorch
- CUDA
- LLM
- Agentic AI
-
Deep LearningIntroduction to Panoptic Segmentation: A Tutorial
Panoptic segmentation unifies semantic and instance segmentation assigning class labels and unique IDs to every pixel in an image.
-
Deep LearningEvaluation metrics for object detection and segmentation: mAP
How IoU, precision-recall curves, and mean Average Precision (mAP) are used to evaluate object detection and segmentation models.
-
Deep LearningQuick intro to Instance segmentation: Mask R-CNN
Instance segmentation with Mask R-CNN: combining object detection and semantic segmentation to identify and segment each object instance separately.
-
Deep LearningQuick intro to semantic segmentation: FCN, U-Net and DeepLab
An introduction to semantic segmentation, pixel-level classification using Fully Convolutional Networks, U-Net, and DeepLab architectures.
-
Deep Learning
Converting FC layers to CONV layers
How and why to replace fully connected layers with equivalent convolutional layers, enabling CNNs to accept arbitrary input sizes.
-
PersonalTwo Years of Technical Fridays
Marking two years of Technical Fridays, with over 10,000 global readers and a focus on computer vision going forward.
-
Speech RecognitionIntroduction to Automatic Speech Recognition
The fundamentals of Automatic Speech Recognition (ASR), acoustic models, Hidden Markov Models, and how Bayes' rule drives decoding.
-
Deep LearningData augmentation
How data augmentation like flipping, rotation, color jittering artificially expands training data to build more generalizable deep learning models.
-
Deep LearningGenerative Adversarial Networks variants: DCGAN, Pix2pix, CycleGAN
An overview of GAN variants, DCGAN for image generation, Pix2pix for paired image translation, and CycleGAN for unpaired style transfer.
-
Deep Learning
Layer-specific learning rates
Why using different learning rates per layer in deep networks can compensate for vanishing gradients and improve transfer learning fine-tuning.