Direct-to-consumer genetic testing Genetic testing is a medical test to know about certain things of a person like their disease traits, risk to certain diseases, how effective a drug will be on their body etc. from their DNA samples. Historically, genetic testing is done through healthcare providers. But with the rise of direct-to-consumer genetic testing […]
I Taught these AI to Dance on Drake’s Song using PoseNet
Code is available in GitHub, I taught these AI to dance on In-My-Feelings song by Drake using PoseNet and Tensorflow.js I have used the Pose Detection model called PoseNet implemented in Tensorflow.js. The original repository can be found in https://github.com/tensorflow/tfjs-models/tree/master/posenet. I have modified the codes to enable the following Loads a pre-trained PoseNet model Runs […]
Training Single Shot Multibox Detector, Model Complexity and mAP
This post is a continuation to my previous post Object Detection with Single Shot Multibox Detector. If you have not read the first part, I recommend you to read that first for a better understanding. In this post, along with some important concepts regarding training, I have talked about my observation of the model complexity […]
Object Detection with Single Shot Multibox Detector
The current frameworks for object detection task can be categorized into two main types. One category of frameworks uses a two-step pipeline – first it generates region proposals using improved algorithms other than sliding windows, then passes the regions to CNN and SVM for feature extraction followed by classification and localization. The other category unifies […]
Convolutional Neural Network Basics
Convolutional neural networks or CNNs are deep neural networks considered as the most representative model of deep learning. CNNs extend on traditional neural networks by combining both fully-connected hidden layers and locally-connected convolutional layers. In traditional neural networks, each neuron in the hidden layer is fully-connected to all neurons in the preceding layer. However, in […]
Neural Network Demystified Part lll – Gradient Descent and Backpropagation
This post is the third and last part of the series Neural Network Demystified. If you haven’t read the first two parts please check Neural Network Demystified Part l – Building Blocks and Activation Functions and Neural Network Demystified Part lI – Deep Neural Network first. Training a Neural Network Neural networks are used for […]
Neural Network Demystified Part ll – Deep Neural Network
This post is the second part of the series Neural Network Demystified. If you haven’t read the first part please check Neural Network Demystified Part I – Building Blocks and Activation Functions first. Arti ficial Neural Networks Artifi cial Neural Networks (ANNs) are motivated by the nervous system of the human brain where approximately 86 billion neurons are […]
Neural Network Demystified Part I – Building Blocks and Activation Functions
Building Blocks of a Neural Network Although the original intention of designing a neural network was to simulate the human brain system to solve general learning problems in a principled way, in practice neural network algorithms work in much simpler way than a human brain. Current neural networks can be compared to statistical models having […]
My Master’s Thesis in 3 Minutes – 3MT Competition
Conducting quality research on any field is hard, however not as hard as explaining the research to a room full of people with non-technical background, that too in just 3 minutes! As a person who is never afraid of taking challenges, I couldn’t afford to lose the opportunity to participate in the prestigious 3-Minute Thesis […]
How deep is a Deep Neural Net?
As a machine learning researcher, I often get asked this question about “how deep a neural net is called a deep neural net”. After having some good reads and listening to some great AI specialists, I have finally come up with a satisfactory answer to this interesting but a bit tricky question. Before delving deep […]