Today machine learning is largely about statistical pattern discovery and function approximation from large volumes of data. But as computing devices that interact with us in natural language become ubiquitous (e.g., Siri, Alexa, Google Now), and as computer perceptual abilities become more accurate, they open an exciting possibility of enabling end-users to teach machines similar to the way in which humans teach one another.

Natural language interactions, gesturing, demonstrations, teleoperation and other modes of communication offer a new paradigm for machine learning through instruction from humans. This builds on several existing learning paradigms (e.g., active learning, supervised learning, reinforcement learning), but also brings a new set of advantages and research challenges that lie at the intersection of several fields including machine learning, natural language understanding, computer perception, and HCI.

The aim of this workshop is to showcase new research in this area and to engage researchers and practitioners from these diverse fields to explore fundamental research questions such as:

• How do people interact with machines when teaching new tasks and knowledge?
• What novel learning algorithms are needed to learn from human instruction?
• What are the practical and architectural considerations towards building computer systems that can learn from instruction?

We have a great lineup of invited speakers, oral and poster presentations and a panel discussion.

Submit a contribution by Nov 9, 2018!

Organizers:

• Shashank Srivastava (Microsoft Research)
• Igor Labutov (LAER AI)
• Bishan Yang (LAER AI)
• Amos Azaria (Ariel University)
• Tom Mitchell (Carnegie Mellon University)