Ian Howard

Academic profile

Dr Ian Howard

Associate Professor Computational Neuroscience
School of Engineering, Computing and Mathematics (Faculty of Science and Engineering)

Overview

Fingerprint

Network

Research outputs

Similar profiles

The Global Goals

In 2015, UN member states agreed to 17 global Sustainable Development Goals (SDGs) to end poverty, protect the planet and ensure prosperity for all. Ian's work contributes towards the following SDG(s):

Goal 03: SDG 3 - Good Health and Well-beingGoal 04: SDG 4 - Quality EducationGoal 09: SDG 9 - Industry, Innovation, and Infrastructure

About Ian

Research interests

My theoretical research investigates the computational principles underlying learning and intelligent behaviour. I am particularly interested in how internal state, architecture and feedback shape what biological and artificial systems can represent, learn and compute. Specific interests include latent-state representations, pre-structured neural architectures, credit assignment, reward, abstraction and hierarchy, and the distinction between computational expressivity and learnability.

A central aim is to translate theoretical understanding into computational mechanisms, architectures and learning methods that can extend the capabilities of artificial intelligence. This includes investigating how architectural structure and learning interact, how systems maintain and use information over time, and how intelligent behaviour can be achieved under constraints on information and computation. Biological intelligence provides important evidence and inspiration, but its particular mechanisms need not define the limits of artificial systems.

Sensorimotor control provides an experimental route into these questions. My work encompasses human motor learning, speech motor control, haptic interaction and movement assessment. I use behavioural experiments and computational models to investigate state estimation, adaptation, feedback control and stabilising variables, and to test explanations of how biological systems acquire and maintain skilled behaviour.

I also design and build haptic and robotic interfaces and real-time embedded control systems. These provide experimental platforms for investigating learning and interaction, and for testing computational principles in physically meaningful tasks. Embodied, closed-loop control is an important perspective within this work, connecting theoretical questions with measurable behaviour in biological and artificial systems.

Teaching

My teaching covers robotics, autonomous systems, machine learning, sensors and actuators, embedded systems, real-time programming, mobile and humanoid robots, motor control, and control engineering. Across these areas, I am particularly interested in helping students understand autonomy as an embodied control problem, where sensing, estimation, actuation, feedback, learning, and decision-making must be integrated in real physical systems.

Module leader for:

  • ROCO352 Introduction to Machine Learning
  • ELEC352 Real-Time Embedded Programming for Autonomous and AI Systems
  • ROCO322 Autonomous Mobile and Humanoid Robots

Previously module leader for:

  • ROCO219 Control Engineering
  • ROCO224 Introduction to Robotics
  • AINT516Z Topics in Advanced Intelligent Robotics
  • ROCO222 Introduction to Sensors and Actuators
  • SOFT561 Robot Software Engineering
  • SOFT141 Network Programming

Contact Ian

+44 1752 586324