Autoencoders In Machine Learning

1 mainWhen we talk about deep neural networks, we tend to focus on feature learning. Traditionally, in the field of machine learning, people use hand-crafted features. What this means is that we look at the data and build a feature vector which we think would be good and discriminative. Once we have that, we train a model to learn from it. But one of the biggest problems with this approach is that we don’t really know if it’s the best possible representation of the data. Ideally, we would want the machine to learn the features by itself, and then use it to build the machine learning model. Autoencoder is one such neural network which aims to learn how to build optimal feature vector for the given data. So how exactly does it work? How is it used in practice?   Continue reading

What’s The Importance Of Hyperparameters In Machine Learning?

1 mainMachine 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. Now why is that? Where do these parameters come from? How do we deal with this?   Continue reading

What Is AdaBoost?

imageAdaBoost is short for Adaptive Boosting. It is basically a machine learning algorithm that is used as a classifier. Whenever you have a large amount of data and you want divide it into different categories, we need a good classification algorithm to do it. We usually use AdaBoost in conjunction with other learning algorithms to improve their performance. Hence the word ‘boosting’, as in it boosts other algorithms! Boosting is a general method for improving the accuracy of any given learning algorithm. So obviously, adaptive boosting refers to a boosting algorithm that can adjust itself to changing scenarios. But why do those algorithms need AdaBoost in the first place? Can AdaBoost function by itself?   Continue reading

Content Delivery Network – Part 2/2

mainIn the previous post, we discussed about content delivery network (CDN) and why we need it. This post is a continuation of that topic. Here, we will discuss about the pros and cons of using CDN. CDN obviously helps the sites that experience heavy traffic. Most of the times, you will think that just using a CDN will deliver a better performance, but this is not always the case. If you don’t choose your provider carefully, your site will end up suffering. Let’s look at some of the advantages and disadvantages of using CDN.   Continue reading

Content Delivery Network – Part 1/2

mainInternet users today are demanding faster and higher-quality services from their media hosting companies. Being an internet user yourself, you should know that we place a high demand on these services. This is the reason quick access and delivery of rich-media like music, photos, videos etc has become a top priority. Wait a minute, why we need to care about all that? Doesn’t that just happen somewhere on the server? Well, who do you think makes that happen? It’s the people who manage the website. The beautiful site that loads all the high-resolution images for you doesn’t just work magically by itself. It needs to be optimized in a zillion ways for you to not feel the pain. All of your pages, including your photos and videos, will load quickly and instantly if the website owners use the right Content Delivery Network (CDN). Let’s see what this whole thing is about, shall we?   Continue reading

The Genesis Of Genetic Algorithms

genetic algo dna styleLet’s say you have a function and you want to optimize it. In real life, this function can take many forms like choosing the right set of features for your car while keep the price low, picking the best possible apartment considering all the different factors like location, rent, closeness to stores etc, making a business plan, and many other things. In fact, we continuously use optimization in our everyday life without even realizing it. The interesting thing to note is that we don’t get the most optimal answer every time. We just look around for a while and stop when we get a good enough answer. More often than not, these answers are sub-optimal, mostly depending on the initial point we chose. So how do we get to the best answer? There might be billions of options, do we need check all of them to get to this global optimum?   Continue reading

The Power Of A/B

Designing a website is more of an art than a science. There are a million different ways to design a website and achieve a particular goal. We want our websites to eventually become popular and make money. Once the site is designed, it cannot be stagnant for long either. But how do we know if the users will like the new design? User base is critical and losing them is very risky. Once the users lose trust, it’s very difficult to earn it back. We want to take the guesswork out of website optimization and enable making decisions based on real data. By measuring the impact of the changes, you can ensure that every change produces positive results. So how do we do it?   Continue reading