Indus Tech

01/05/2021

A data labeling/annotation job is available:
Description: There is a description for each image and then you have a corresponding image to that description the goal is to clean the description i.e. to make the description such that it actually explains the content of the image. The demo is attached below you can have a look to understand. Inbox me only if you understand the job.
Link to the video: https://drive.google.com/file/d/1RczkAkU6LN3WYuV1P3GcnoaRyLcysOg5/view

16/10/2019

With the latest developments and improvements in the field of deep learning and artificial intelligence, many exacting tasks of Natural Language Processing are becoming facile to implement and execute. Text Generation is one such task which can be be architectured using deep learning models, particularly Recurrent Neural Networks.
Text Generation is a type of Language Modelling problem. Language Modelling is the core problem for a number of of natural language processing tasks such as speech to text, conversational system, and text summarization. A trained language model learns the likelihood of occurrence of a word based on the previous sequence of words used in the text. Language models can be operated at character level, n-gram level, sentence level or even paragraph level.
In this post, I will explain how to create a language model for generating natural language text by implement and training state-of-the-art variation of Recurrent Neural Network which is LSTM.

This projected was originally was for one of my clients on up-work. You can find the code on my Github repo. Unfortunately It does not…

09/09/2019

Machine learning is becoming increasingly relevant in all walks of science and technology. In fact, it’s an integral part of many fields like computer vision, natural language processing, robotics, e-commerce, spam filtering, and so on. The list is potential applications is pretty huge! People working on machine learning tend to build models based on training data, in the hope that those models will perform well on unseen data. As we all know, every model has some parameters associated with it. We want our machine learning models to estimate these parameters from the training data. But as it turns out, there are a few parameters that cannot be estimated using this procedure. These parameters tend have a significant impact on the performance of your model.
Hyperparameters are important because they directly control the behaviour of the training algorithm and have a significant impact on the performance of the model is being trained.
“A good choice of hyperparameters can really make an algorithm shine”. Give a read to the article and know about the parameters or more precisely hyperparameters which makes Neural Networks really powerful.

In the previous story (part A) we discussed the structure and three main building blocks of a Neural Network. This story will take you…

19/06/2019

Humanity has been dreaming of creating intelligent inventions since as far back as 800 BC, when ancient Greeks wrote about mechanical men created by the Gods. In the last century, technology has been progressing exponentially and has brought us to a point where that dream of self-aware robots is no longer associated with magic.
The creation of Artificial Intelligence has allowed us to create amazing programs that can far surpass the abilities of any human.
The key advancement in the field of artificial intelligence that allowed us to do amazing things like create chat-bots and detect malignant tumors was the discovery of neural networks. Before this, programmers created relatively simple regression models to predict and classify data. However, these models had their limitations. In this story we will be looking into the Artificial Neural Networks and some of their Key Elements.

Introduction to Neural Networks and Their Key Elements

31/05/2019

Deep Learning Series Chapter 1: Introduction to Deep Learning. A brief guide.

Currently, AI is progressing rapidly and deep learning is one of the contributors. Deep learning is a branch of machine learning that…

22/05/2019

All you need to know about Recurrent Neural Networks: The art behind voice assistants.

There is a lot of buzz now a days about machine learning, deep learning and artificial neural networks. Programmers just want to work with…