دانلود کتاب یادگیری عمیق تکاملی

Deep learning (DL) has become the ubiquitous technology most associated with artificial intelligence and the explosion of machine learning. It has grown from once being considered a pseudo-science (The Deep Learning Revolution by Terrence J. Sejnowski) to now being used in mainstream applications from diagnosing breast cancer to driving cars. While many consider it the technology of the future others take a more pragmatic and practical approach to its growing complexity and thirst for data.

As deep learning becomes more complex, we force feed it more and more data with the hopes of some grand epiphany over a particular domain. Unfortunately, this is rarely the case and all too frequently we are left with bad models, poor results, and angry bosses. This is a problem that will continue to persist until we develop a process around our DL systems.

The process of building effective and robust deep learning systems mirrors or should mirror that of any other machine learning or data science project. While some phases may vary in required resources and complexity all steps will remain the same. What is often lacking in the relatively new DL world is a tool belt that can help automate some of those processes.