Machine Learning is one type of Artificial Intelligence (AI) that makes the computers to learn without being programmed explicitly.

It focuses on development of computer programs that can change when exposed to new data.

Machine Learning tasks are classified into 3 categories, depending on the nature of learning signal or feedback of a learning system. They are as follows:

  1. Supervised Learning: Here, the teacher gives example inputs and their desired outputs to the computer. The goal is to learn a rule that maps inputs to outputs.
  2. Unsupervised Learning: Here nothing is given to the computer, the learning system itself has to find structure in its input. The goal is discover hidden patterns in the data.
  3. Reinforcement Learning: Here the computer program must perform a certain goal dynamically. The program gets feedback as rewards and punishments.

Top 10 Problems of machine learning for 2017 are as follows:

  1. Natural Language processing : Understanding language is still a challenge for even the deepest networks.
  2. Differential Neural Computers: These are a special type of memory augmented neural networks which can think but cannot scale.
  3. Memory augmented neural networks are a type of neural networks which has a memory blocks which can be read and written to by the network. We need to find the better way to discover facts, store and use them effectively to solve problems.
  4. Object Detection: Machine Learning cannot understand or detect images.
  5. Attention: Systems cannot grab attention in neural networks. So, we need to build attention mechanisms in neural networks to make them more better.
  6. Machine learning cannot learn by observations and listening.
  7. One-shot learning: The ability to learn with fewer or less examples.
  8. Effective Response Generation: The ability to generate contextual responses.
  9. Automated learning from a repository of resources: Learning from other resources by making a graph connected sense.
  10. Facial Identification over varying feature space: Facial recognition is not perfect even though it is a primary requirement.