Interest in machine learning has exploded over the past decade. You see machine learning in computer science programs, industry conferences, and the Wall Street Journal almost daily. For all the talk about machine learning, many conflate what it can do with what they wish it could do. Fundamentally, machine learning is using algorithms to extract information from raw data and represent it in some type of model. We use this model to infer things about other data we have not yet modeled.
What is Deep Learning?Deep learning has been a challenge to define for many because it has changed forms slowly over the past decade. One useful definition specifies that deep learning deals with a “neural network with more than two layers.” The problematic aspect to this definition is that it makes deep learning sound as if it has been around since the 1980s. We feel that neural networks had to transcend architecturally from the earlier network styles (in conjunction with a lot more processing power) before showing the spectacular results seen in more recent years.
How Does Machine Learning Work?Fundamentally, machine learning is based on algorithmic techni‐ ques to minimize the error in this equation through optimization. In optimization, we are focused on changing the numbers in the x column vector (parameter vector) until we find a good set of values that gives us the closest out‐ comes to the actual values. Each weight in the weight matrix will be adjusted after the loss function calculates the error (based on the actual outcome, as shown earlier, as the b column vector) produced by the network. An error matrix attributing some portion of the loss to each weight will be multiplied by the weights themselves.
Key Takeaways from ‘Deep Learning: A Practitioner’s Approach’
- A Review of Machine Learning
- Fundamentals of Deep Networks