How To Train A Neural Network In Python – Part I

1 mainDeep learning uses neural networks to build sophisticated models. The basic building blocks of these neural networks are called “neurons”. When a neuron is trained to act like a simple classifier, we call it “perceptron”. A neural network consists of a lot of perceptrons interconnected with each other. Let’s say we have a bunch of inputs and the corresponding desired outputs. The goal of deep learning is to train this neural network so that the system outputs the right value for the given set of inputs. This process basically involves tuning each neuron in the network until it behaves a certain way. So what exactly is this perceptron? How do we train it in Python?   Continue reading

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 Is Random Walk?

1 mainConsider the following situation. We have a drunkard who is clinging to a lamppost, and now he decides to start walking. He is in the middle of the street and the road runs from east to west. In his inebriated state, he is as likely to take a step towards the east as he is towards the west. It just means that there is a 50% chance that he will go in either direction. From each new position, he is again as likely to go east or west. Each of his steps are of the same length but in random direction. After having taken ‘n’ number of steps, he is to be found standing at some position on the street. This is what a random walk is. We can plot the position against the number of steps taken for any particular random walk. Now the question is, can we model his movement so that we can predict where he will be after taking ‘n’ steps?   Continue reading

Purkinje Effect

mainEver wondered why the colors seem to change at night? For example, if you look at an air painting, you can see how the colors of objects look radically different in very low light just before dawn or dusk. Consider a red rose, for instance. We know that the flower’s petals are bright red against the green of the leaves in daylight. But, take a look at dusk and you will see that suddenly the contrast is reversed, with the red flower petals now appearing dark red or dark warm gray, and the leaves appearing relatively bright. Bright red doesn’t remain bright red anymore, and green doesn’t remain green either. They all become a bit monochromatic and it becomes difficult to separate them. Why does this happen?   Continue reading

Can Machines Be Truly Independent?

thinking computerIn my previous blog post, we discussed about how we can measure a computer’s intelligence. When we talk about machine intelligence, what exactly are we talking about? Are we just talking about machines mimicking the human ways and mannerisms in the best possible way? No matter what the machines do, they are still following a predefined sequence of steps or an algorithm that dictates the sequence of steps. The field of artificial intelligence has been trying for a long time to put actual intelligence into a machine, but we are still far from it. The question then would be, can machines be truly independent?   Continue reading

What Does Backpropagation Mean?

feedbackPeople started working on artificial intelligence back in the late ’60s. After they came up with the concept of perceptron, this field looked very promising. But as the years passed by, no significant development took place even after making several attempts from multiple directions! As people were beginning to lose hope, backpropagation came into picture and breathed new life into this field. Backpropagation was the result of pioneering work by mathematicians and computer scientists, which eventually led to a successful revival of artificial intelligence! So what exactly is backpropagation? How is it used in real life?   Continue reading

Perceiving The Perceptron

multi layer perceptronIf you are hearing the word “perceptron” for the first time, it sounds a lot like a futuristic robot which can perceive things right? Well, that’s not exactly what it means! Perceptron is a machine learning algorithm for supervised classification. It is one of the very first algorithms to be formulated in the field of artificial intelligence. When it first came out, it was very promising. But over the following years, the performance didn’t exactly reach the expectations. It was studied for many years and the theory was modified and extended in a lot of ways. Now, it has become an integral part in the field of artificial neural networks. So what exactly is a perceptron? Where do we use it in real life?   Continue reading