Machine Learning is the common buzzword among data scientists. You just cannot miss the dialect of ML if you wish to begin your career in data sciences. You may be bombarded with terms such as Regression, Clustering, Classification, Neural Networks... the list never ends. But worry no more, as the following free resources will help you trace baby steps in the land of machine learning.\n\nOne specific core branch of ML is deep learning (DL). People often confuse machine learning and deep learning to be the same, but to a larger context it isn't. If rightly put, deep learning forms a part of machine learning. In this article, we present you 5 worth-reading resources (in no particular order) that can help you learn deep learning from the beginning assuming you have no prior knowledge of ML, without overwhelming you.\n\n1. Deep Learning by \u00a0Ian Goodfellow, Yoshua Bengio and Aaron Courville (Book-2016) \n\n\n\nThe standalone book for someone who does not have a single clue about deep learning jargon. This book is often quoted as \u2018The Bible of Deep Learning\u2019 by experts. Even Elon Musk himself said this is the only comprehensive book available on the subject, as it offers an interesting pedagogic view of mathematical topics such as linear algebra, probability theory information theory, numerical computation, and the basics of machine learning. It provides a broader understanding of deep learning techniques used by data science and business intelligence professionals, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology. Practical applications such as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics and videogames are also explored. This book is available online in the HTML version and can also be purchased here, hardcover as well as Kindle edition.\n\n[divider top="no" size="1"]\n\n2. Deep Learning Course by Udacity & Google (Website)\n\n\n\nWhat more can you say when tech-giant Google teams up with Udacity, a popular online education portal, bringing out a free course. Sounds interesting, right?. Well, the course is available for anyone interested to start with machine learning alongside deep learning and gradually advance to the complex aspects of machine intelligence. The course uses TensorFlow to work on projects, thereby helping you gain practical as well as theoretical knowledge. All one needs to do is sign up for the course and they are good to go. It is self-paced, so the learner can take his own time to complete the course, suiting the ability and knowledge.\n\n[divider top="no" size="1"]\n\n3. Stanford University Online Open Course on Deep Learning (Website)\n\n\n\nAnyone willing to get direct insights from the experts themselves, this free online course will definitely fulfill their deep learning desire. Compiled by deep learning experts Samy Bengio, Tom Dean, deep learning scientists at Google and Andrew Ng, former Vice President and Chief Scientist at Baidu and a Professor at Stanford University (he is the pioneer behind Stanford\u2019s Massive Open Online Courses abbreviated MOOC), the course offers video explanation of topics under linear regression, logistic regression and regularisation such as cost function, vector implementation, polynomial regressions and variations observed among regressions. A definite must go for tech enthusiasts keen on understanding deep learning basics.\n\n[divider top="no" size="1"]\n\n4. Deep Learning Tutorial by University of Montreal (Book-2015)\n\nDeveloped by LISA lab at University of Montreal, this free and concise tutorial presented in the form of a book explores the basics of machine learning. The book emphasizes with using the Theano library (developed originally by the university itself) for creating deep learning models in Python. The book starts by suggesting users to download the MNIST(Modified National Institute of Standards and Technology) dataset to work with the learning. Several notations such as data labels and math conventions are followed for better interpretation. The tutorial is categorised into supervised algorithms (must be read in order) and unsupervised\/semi-supervised algorithms (can be read in random and generally used to train dataset).\n\n[divider top="no" size="1"]\n\n5. WildML (Website)\n\n\n\nStarted by Denny Britz, an ex-employee of Google LLC and a Stanford University graduate, this site offers tips and techniques for a deep learning beginner. He posts tutorials and articles on contemporary topics such as Reinforcement Learning and Neural networks. In addition,there is a separate section of deep learning index on the website that allows learners to get a gist of all the terms to familiarise with deep learning (backpropagation, pooling, Seq2Seq, to mention a few). This site is a must for everyone willing to explore newer problems that can be addressed using deep learning apart from just getting to know information related to it. You can also follow Denny Britz on Twitter to check out the latest news and trends in deep learning.