Digital signal processing (DSP) is one of the ‘foundational’ but somewhat invisible, engineering topics of the modern world, without which,
many of the technologies we take for granted: the digital telephone,
digital radio, television, CD and MP3 players, WiFi, radar, to name
just a few, would not be possible. A relative newcomer by comparison,
statistical machine learning is the theoretical backbone of exciting technologies that are by now starting to reach a level of ubiquity, such as
automatic techniques for car registration plate recognition, speech recognition, stock market prediction, defect detection on assembly lines, robot
guidance and autonomous car navigation. Statistical machine learning
has origins in the recent merging of classical probability and statistics
with artificial intelligence, which exploits the analogy between intelligent
information processing in biological brains and sophisticated statistical
modelling and inference.
DSP and statistical machine learning are of such wide importance to
the knowledge economy that both have undergone rapid changes and
seen radical improvements in scope and applicability. Both DSP and
statistical machine learning make use of key topics in applied mathematics such as probability and statistics, algebra, calculus, graphs and networks. Therefore, intimate formal links between the two subjects
exist and because of this, an emerging consensus view is that DSP and
statistical machine learning should not be seen as separate subjects.