In a highly-publicised recent contest the AlphaGo model beat the top-ranked Go player over a number of games, further enhancing the mystery and excitement surrounding this machine learning technique.ĭeep learning is not an easy subject to learn and requires some undergraduate mathematical prerequisites in order to get started. In the last couple of years one of the leading deep learning firms, Google DeepMind, has managed to use a particular technique known as deep reinforcement learning to beat humans at Atari 2600 games. However it has also been widely hyped - the answer to all machine learning problems - and is often misunderstood due to its steep learning curve. It has produced state-of-the-art results in areas as diverse as computer vision, image recognition, natural language processing and speech recognition.
Over the last ten years the subject of deep learning has been one of the most discussed fields in machine learning and artificial intelligence.