Weighted Least Squares - Parameter Estimation
A special case of Generalized Least Square, an extension of Ordinary Least Square used in a regression model when data points have inconsistent variance of errors
Topic
Artificial Intelligence
A collection of 8 issues
Maxout Activation Function
General purpose neuron activation function that outputs maximum value from a set of linear functions in output range (-∞ , ∞)
Softmax Activation Function
Math functions that calculate weighted sum of inputs and adds bias to give non-linearity to output of neuron.
Word Embeddings: Theory and Analysis
To implement natural language processing tasks, we deal with various kinds of discrete types. The most common being words. Words originate from a finite set; vocabulary. Other examples are characters, part-of-speech tags, named
entities, named entity types, parse features, items in a product catalog and more.
Any input feature that
Curated List of Machine Learning Online Resources
During my time of learning machine learning, specially Deep Learning focused on Semantic Segmentation and Image Matting, I collected these useful bookmarks that I would like to share. I hope it helps you too.
machine learning, deep learning bookmarks: github links, tutorials, how-to guides, deep learning free courses, image datasets,
Notes on Convolutional Neural Network
Preliminary knowledge of computer vision is good for readers.
You may also like articles on Image Manipulation and Object Detection.
We start with a simple analogy about what is an artificial neuron. It is a math function but a digital one. And it tries to function similar to our brain&
Beginner's Guide to Image Manipulation Terms
An image is
* array of numbers
* made up of a matrix of pixels
* each pixel having an intensity between 0-255.
A JPEG image
* 3D matrix
* with channels for red, green, and blue pixel intensities.
For each pixel in the matrix, the intensity values across these three channels combine to create
Fundamentals of Object Detection
Object Detection
Ability to detect multiple classes of objects and identify them within a best possible concise bounding boxes in an image or video or live camera feed. There are various algorithms to achieve object detection like R-CNN, Fast R-CNN, Faster R-CNN, SSD and YOLO.
For eg: let’s classify