Machine Learning Archives | CloudxLab Blog

Natural Languages and AI

During one of the keynote speeches in India, an elderly person asked a question: why don’t we use Sanskrit for coding in AI. Though this question might look very strange to researchers at first it has some deep background to it.

Long back when people were trying to build language translators, the main idea was to have an intermediate language to and from which we could translate to any language. If we build direct translation from a language A to B, there will be too many permutations. Imagine, we have 10 languages, and we will have to build 90 (10*9) such translators. But to come up with an intermediate language, we would just need to encode for every 10 languages and 10 decoders to convert the intermediate language to each language. Therefore, there will be only 20 models in total.

So, it was obvious that there is definitely a need for an intermediate language. The question was what should be the intermediate language. Some scientists proposed that we should have Sanskrit as the intermediate language because it had good definitive grammar. Some scientists thought a programming language that can dynamically be loaded should be better and they designed a programming language such as Lisp. Soon enough, they all realized that both natural languages and programming languages such as Lisp would not suffice for multiple reasons: First, there may not be enough words to represent each emotion in different languages. Second, all of this will have to be coded manually.

The approach that became successful was the one in which we represent the intermediate language as a list of numbers along with a bunch of numbers that represent the context. Also, instead of manually coding the meaning of each word, the idea that worked out was representing a word or a sentence with a bunch of numbers. This approach is fairly successful. This idea of representing words as a list of numbers has brought a revolution in natural language understanding. There is humongous research that is happening in this domain today. Please check GPT-3, Dall-E, and Imagen.

If you subtract woman from Queen and add Man, what should be the result? It should be King, right? This can be easily demonstrated using word embedding.

Queen — woman + man = King

Similarly, Emperor — man + woman = Empress

Yes, this works. Each of these words is represented by a list of numbers. So, we are truly able to represent the meaning of words with a bunch of numbers. If you think about it, we learned the meaning of each word in our mother tongue without using a dictionary. Instead, we figured the meaning out using the context.

In our mind, we have sort of a representation of the word which is definitely not in the form of some other natural language. Based on the same principles, the algorithms also figure out the meaning of the words in terms of a bunch of numbers. It is very interesting to understand how these algorithms work. They work on similar principles to humans. They go through the large corpus of data such as Wikipedia or news archives and figure out the numbers with which each word can be represented. The problem is optimization: come up with those numbers to represent each word such that the distance between the words existing in a similar context is very small as compared to the distance between the words existing in different contexts.

The word Cow is closer to Buffalo as compared to Cup because Cow and buffalo usually exist in similar contexts in sentences.

So, in summary, it is very unreasonable to pursue that we should still be considering a natural language to represent the meaning of a word or sentence.

I hope this makes sense to you. Please post your opinions in the comments.

Coding Backpropagation and Gradient Descent From Scratch without using any libraries

Backpropagation is considered one of the core algorithms in Machine Learning. It is mainly used in training the neural network. And backpropagation is basically gradient descent. What if we tell you that understanding and implementing it is not that hard? Anyone who knows basic Mathematics and has knowledge of the basics of Python Language can learn this in 2 hours. Let’s get started.

Though there are many high-level overviews of the backpropagation and gradient descent algorithms what I found is that unless one implements these from scratch, one is not able to understand many ideas behind neural networks.

Writing Custom Optimizer in TensorFlow Keras API

Recently, I came up with an idea for a new Optimizer (an algorithm for training neural network). In theory, it looked great but when I implemented it and tested it, it didn’t turn out to be good.

Some of my learning are:

Neural Networks are hard to predict.
Figuring out how to customize TensorFlow is hard because the main documentation is messy.
Theory and Practical are two different things. The more hands-on you are, the higher are your chances of trying out an idea and thus iterating faster.

I am sharing my algorithm here. Even though this algorithm may not be of much use to you but it would give you ideas on how to implement your own optimizer using Tensorflow Keras.

A neural network is basically a set of neurons connected to input and output. We need to adjust the connection strengths such that it gives the least error for a given set of input. To adjust the weight we use the algorithms. One brute force algorithm could be to try all possible combinations of weights (connections strength) but that will be too time-consuming. So, we usually use the greedy algorithm most of these are variants of Gradient Descent. In this article, we will write our custom algorithm to train a neural network. In other words, we will learn how to write our own custom optimizer using TensorFlow Keras.

Understanding Computer Vision with Deep Learning – Free Webinar

CloudxLab conducted a successful webinar on “Introduction to Machine Learning” on the 15th of October, 2019. It was a 2-hour session in which the instructor explained the concepts based on Understanding Computer Vision with Deep Learning.

More than 250 learners around the globe attended the webinar. The participants were from countries namely; United States, Canada, Australia, Indonesia, India, Thailand, Philippines, Malaysia, Macao, Japan, Hong Kong, Singapore, United Kingdom, Saudi Arabia, Nepal, & New Zealand.

Big Data vs Machine Learning

Every day the world is advancing into the new level of industrialization and this has resulted in the production of a vast amount of data. And, at initial stages, people started considering it as a bane, but later they found out that it’s a boon. So, they started using this data in a productive way. Big data and machine learning are terminologies based on the concept of analyzing and using the same data. Let’s get into more details.

CloudXLab is proud to sponsor RACE360 as a Technology Partner.

RACE360, an Emerging Technology Conference 2019 (Powered by The Times of India) is happening on Wed, Aug 28th at The Lalit Ashok, Bengaluru. It is presented by REVA University, Bengaluru (REVA Academy for Corporate Excellence (RACE)).

Stages of Artificial Intelligence

The emergence of Artificial Intelligence has played an essential role in revolutionizing the technical industry. According to many people, Artificial Intelligence is something that makes their work easy; well, it is just one of the qualities of Artificial Intelligence.

What is Artificial Intelligence?

According to Wikipedia, Artificial Intelligence “is intelligence demonstrated by machines, in contrast to the natural intelligence displayed by humans.”

Artificial intelligence can be categorized into several stages, depending upon the role they play. In this article, we will go through all of these stages, including their real-world application.

Upskill your workforce in partnership with CloudxLab

Henry Ford (Founder of Ford Motor Company) once said- “The only worse thing than training your employees and having them leave is not training them and having them stay”.

Most organizations face this dilemma and sometimes choose not to upskill their workforce only to impede its own growth and relinquish opportunities of gaining competitive advantage. While organizations actively promoting workforce learning & development (L&D) often face indifferent employee behaviours to such initiatives. There are other concerns as well, such as- customised learning platforms, hands on learning, training quality, accreditation, post training support and what not……..

Things to Consider While Managing Machine Learning Projects

Generally, Machine Learning (or Deep Learning) projects are quite unique and also different from traditional web application projects due to the inherent complexity involved with them.

The goal of this article is, not to go through full project management life cycle, but to discuss a few complexities and finer points which may impact different project management phases and aspects of a Machine Learning(or Deep Learning) project, and, which should be taken care of, to avoid any surprises later.

Below is a quick ready reckoner for the topics that we will be discussing in this article.

Conference on Computer Vision at Google Asia, Singapore

The deep learning algorithms and frameworks have changed the approach to computer vision entirely. With the recent development in computer vision with Convolutional Neural Networks such as Yolo, a new era has begun. It would open doors to new industries as well as personal applications.

After the successful bootcamps held at IIT Bombay, NUS Singapore, RV College of Engineering, etc, CloudxLab in collaboration with IoTSG and Google Asia conducted a successful conference on Understanding Computer Vision with AI using Tensorflow on May 11, 2019, at Google Asia, Singapore office.