Deep Tech
Reporting, analysis and features from AIM's Deep Tech section.
Hand-on Implementation of CycleGAN, Image-to-Image Translation using PyTorch
CycleGAN is designed for image-to-image translation, and it learns from unpaired training data. It gives us a way to learn the mapping between one image domain and another using an unsupervised approach.
Amit Singh ·
Guide To Parsehub: A No-Code, GUI Based Data Scraping tool
Mohit Maithani ·
MIT Develops A New System That Creates Different Kind Of Robots
Ram Sagar ·
Loss Functions in Deep Learning: An Overview
Neural Network uses optimising strategies like stochastic gradient descent to minimize the error in the algorithm. The way we actually compute this error is by using a Loss Function. It is used to quantify how good or bad the model is perf…
Ankit Das ·
Activation Functions in Neural Networks: An Overview
In this article, I’ll discuss the various types of activation functions present in a neural network.
Jayita Bhattacharyya ·
ML Behind Your Favorite Google Meet Backgrounds
Ram Sagar ·
Hands-on Linear Regression Using Sklearn
In today’s article, we will be taking a look at how to predict the rating of cereals. The problem statement is to predict the cereal ratings where the columns give the exact figures of the ingredients. Link to the data set is mentioned bel…
Bhavishya Pandit ·
Hands-On Guide To Develop Speech To Text Converter Using Python and Google API
In this article, we will build a simple speech to text converter with Python and the google cloud API.
Bhoomika Madhukar ·
Google Teases Large Scale Reinforcement Learning Infrastructure
Ram Sagar ·
How To Avoid Overfitting In Neural Networks
In this article, we will: Learn the different techniques to avoid overfitting of the model and Implement these techniques to a deep learning model
Bhoomika Madhukar ·
Visualizing Sentiment Analysis Reports Using Scattertext NLP Tool
Scattertext is an open-source python library which is used with the help of spacy to create beautiful visualizations of what words and phrases are more characteristics of a given category.
Himanshu Sharma ·
How to Build Your Own Face Filter With OpenCV?
In this article, we will learn about the implementation of face filters using a 68 point landmark detector and OpenCV.
Bhoomika Madhukar ·
Practical Comparison of Transfer Learning Models in Multi-Class Image Classification
In this article, we will compare the multi-class classification performance of three popular transfer learning architectures - VGG16, VGG19 and ResNet50. These all three models that we will use are pre-trained on ImageNet dataset. For the…
Dr. Vaibhav Kumar ·
Step-by-Step Building Block For Machine Learning Models
Rohit Dwivedi ·
Using Grad-CAM to Visually Verify the Performance of CNN Model
Bhoomika Madhukar ·
OpenAI & Uber AI Proposed A New Approach To Neural Architecture Search
Ambika Choudhury ·
A New Paradigm Of Object Detection: Using Transformers
Ram Sagar ·
Now You Can Generate Music From Scratch With OpenAI's Neural Net Model
Ambika Choudhury ·
Why Deep Learning Is A Costly Affair
Ram Sagar ·
Meet This Week’s MachineHack Champions Who Cracked The ‘Message Polarity Prediction’ Hackathon
Amal Nair ·