Machine learning, a field of artificial intelligence, refers to the process in which a machine is trained to learn from data without explicitly being programmed to do so. The process of machine learning is iterative, and as machines are fed more data, they are able to independently adapt. There are three learning approaches that you will explore in this module: supervised learning, unsupervised learning, and reinforcement learning. Supervised learning, arguably the most common learning approach, refers to the type of learning where a machine learns to map an input variable to an output variable based on labelled examples. The labelled examples constitute what is known as a training set.
Data has become the new currency now and when the new norm of the life will be push us more towards adoption of digital products, data will play crucial role in determining consumer behaviour and personalising the digital solution. The demand for the digital products will grow day by day and the responsibility of a product manager will also increase, which will push them to learn new skills and technology. I will keep on sharing my experience and learning with fellow product professionals to solve consumers problem in a better way. Let us start our journey with a brief understanding of machine learning. Machine learning is an application of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience.
Unsupervised learning helps to find a hidden jewel in data by grouping similar things together. Data have no target attribute. The algorithm takes training examples as the set of attributes/features alone. In this post, I have summarised my whole upcoming book "Unsupervised Learning – The Unlabelled Data Treasure" on one page. This one-page guide is to know everything about unsupervised learning on a high level.
Machine Learning is a very large field that aims to provide machines with human-like capabilities of learning and making predictions by acquiring skills or knowledge from historical data. Due to its rapidly expanding capabilities of handling even the most complex of tasks with little to no human intervention with the utmost robustness and speed, it has been a buzz in the software industry. In summary, as quoted by Arthur Samuel, Machine Learning "gives computers the ability to learn without being explicitly programmed." As depicted in the below figure, in stark contrast to traditional programming where data and program are fetched to the computer to get the desired output, a machine learning algorithm takes in data and output to the computer to get the desired programme. The process of converting experience into knowledge is called learning.
We propose the application of a semi-supervised learning method to improve the performance of acoustic modelling for automatic speech recognition based on deep neural net- works. As opposed to unsupervised initialisation followed by supervised fine tuning, our method takes advantage of both unlabelled and labelled data simultaneously through mini- batch stochastic gradient descent. We tested the method with varying proportions of labelled vs unlabelled observations in frame-based phoneme classification on the TIMIT database. Our experiments show that the method outperforms standard supervised training for an equal amount of labelled data and provides competitive error rates compared to state-of-the-art graph-based semi-supervised learning techniques.