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.
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.
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.
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.
Let us say, you have trained, fine-tuned and tested Machine Learning(ML) model – sgd_clf, which was trained and tested using SGD Classifier on MNIST dataset. And now you want to deploy it in production, so that consumers of this model could use it. What are different options you have to deploy your ML model in production?
Mathematics is the science which deals with the logic of quantity, shape, and arrangement. Undeniably, math is all around us, in fact in everything we do. It wouldn’t be wrong to say, math is the building block for everything in our daily life period. Money, sports, architecture (ancient and modern), television, mobile devices, and even art, all of it has some mathematical concepts involved in it.
In India, mathematics has its origins in Vedic literature which is nearly four thousand years old. It should come as no surprise that the concept of number ‘0’ was discovered in India; also, various treatises on mathematics were authored by Indian mathematicians. The techniques of trigonometry, algebra, algorithm, square root, cube root, negative numbers, and the most significant decimal system are concepts which were discovered by Indian mathematician from ancient India and are employed worldwide even today.
One of the classic problem that has been used in the Machine Learning world for quite sometime is the MNIST problem. The objective is to identify the digit based on image. But MNIST is not very great problem because we come up with great accuracy even if we are looking at few pixels in the image. So, another common example problem against which we test algorithms is Fashion-MNIST.
Fashion-MNIST is a dataset of Zalando’s fashion article images —consisting of a training set of 60,000 examples and a test set of 10,000 examples. Each instance is a 28×28 grayscale image, associated with a label.
Usually, the learners from our classes schedule 1-on-1 discussions with the mentors to clarify their doubts. So, thought of sharing the video of one of these 1-on-1 discussions that one of our CloudxLab learner – Leo – had with Sandeep last week.
Below are the questions from the same discussion.
You can go through the detailed discussion which happened around these questions, in the attached video below.
What computing did to the usual industry earlier, Machine Learning is doing the same to usual rule-based computing now. It is eating the market of the same. Earlier, in organizations, there used to be separate groups for Image Processing, Audio Processing, Analytics and Predictions. Now, these groups are merged because machine learning is basically overlapping with every domain of computing. Let us discuss how machine learning is impacting e-commerce in particular.
The first use case of Machine Learning that became really popular was Amazon Recommendations. Afterwards, the Netflix launched a challenge of Movie Recommendations which gave birth to Kaggle, now an online platform of various machine learning challenges.
Before I dive deep into the details further, lets quickly brief the terms that are found often confusing. AI stands for Artificial Intelligence which means being able to display human-like intelligence. AI is basically an objective. Machine learning is making computers learn based on historical or empirical data instead of explicitly writing the rules. Artificial Neural networks are the computing constructs designed on a similar structure like the animal brain. Deep Learning is a branch of machine learning where we use a complex Artificial Neural network for predictions.
