Blog

As the AI boom progresses, there is a definite transition, moving intelligent processes to end devices from their original home in the cloud and big data centers with tremendous compute power.

Organizations all across the globe are recognizing the need for machine learning practices on mobile devices like smartphones and the ability to perform powerful AI-enabled tasks natively on gadgets, machines, vehicles, and more. Qualcomm is one such tech giant trying to shape the edge AI sector with its new line of ML offerings.

Continue reading Using the Snapdragon Neural Processing Engine for efficient edge deployment of ML models

Google’s sign-in provider is a convenient way to allow users to register and log in in a React Native app. It can provide a familiar onboarding experience to the user and can act as a single source of authentication. Using this, you don’t have to take care of functionalities such as email verification, forgot password, resetting passwords, and so on.

Continue reading Integrating Google Sign-in Provider with a React Native app

Natural Language Processing (NLP) is a field at the intersection of computer science, artificial intelligence, and linguistics. The goal is for computers to process or “understand” natural language in order to perform tasks like Language Translation and Question Answering.

With the rise of voice interfaces and chatbots, NLP is one of the most important technologies of the information age a crucial part of artificial intelligence. Fully understanding and representing the meaning of language is an extremely difficult goal. Why? Because human language is quite special.

Continue reading The 7 NLP Techniques That Will Change How You Communicate in the Future (Part I)

With recent developments in deep learning, neural networks are getting larger and larger. For example, in the ImageNet recognition challenge, the winning model, from 2012 to 2015, increased in size by 16 times. And in just one year, for Baidu’s Deep Speech model, the number of training operations increased by 10 times.

Continue reading The 5 Algorithms for Efficient Deep Learning Inference on Small Devices

Imagine you have trained an image classification model whose performance seems a bit poor—did you know there’s more you can do to improve such a model and reduce its bias? You’ve done a lot in creating your model pipeline and then building a predictive model using neural networks, yet its not improving as you expected

Continue reading Overcoming overfitting in image classification using data augmentation

Deep learning and unsupervised feature learning have shown great promise in many practical applications. State-of-the-art performance has been reported in several domains, ranging from speech recognition and image recognition to text processing and beyond.

It’s also been observed that increasing the scale of deep learning—with respect to numbers of training examples, model parameters, or both—can drastically improve accuracy. These results have led to a surge of interest in scaling up the training and inference algorithms used for these models and in improving optimization techniques for both.

Continue reading The 4 Research Techniques to Train Deep Neural Network Models More Efficiently

This tutorial documents a GitHub project called GARI (Genetic Algorithm for Reproducing Images). The project is available here:

Before discussing the details of the project, let’s run through a quick overview of it.

The GARI project accepts an image as input. This image can have one or more channels (i.e. the image could be binary, gray, or color, such as RGB). RGB is the most popular color model that produces any color as a combination of the 3 color channels Red, Green, and Blue. Hence its abbreviation.

Continue reading Reproducing Images using a Genetic Algorithm with Python