Pytch is a free web-based coding environment (www.pytch.org)designed to help learners transition from block-based to text-based programming languages.The project aims to make this leap more accessible, engaging and intuitive, allowing learners to build on the skills they have developed in Scratch while gradually introducing them to Python syntax and concepts.

In this paper, we investigate student experiences when using the Pytch programming environment. Pytch is a novel system we are developing to ease the transition from block-based to text-based programming through the preservation of the Scratch-style programming model within a Python programming environment. This paper adds to the literature on the problematic transition from block to text programming by describing and analysing the impact on learners of a platform that is focused specifically on the question of this transition. In the in-person workshops described in this paper, students were introduced to the Pytch platform in a classroom environment. Data were collected from a variety of sources to evaluate the effect of Pytch on students, including pre and post surveys, in-class observations, and focus group data. We found high user satisfaction and engagement with Pytch. We also found an increase in user confidence at programming tasks, with a stronger effect for less-experienced participants. These results indicate the usefulness of Pytch in fostering enthusiasm and a sense of achievement, particularly for intermediate and introductory learners in the context of text-based programming. Evaluation of the qualitative data collected during sessions provided valuable insights as to how Pytch supported learners, and what future refinements to the system would be beneficial.

Standard, exact techniques based on likelihood maximization are available for learning auto-regressive process models of dynamical processes. The uncertainty of observations obtained from real sensors means that dynamics can be observed only approximately. Learning can still be achieved via "EM-K"-expectation-maximization (EM) based on Kalman filtering. This cannot handle more complex dynamics, however, involving multiple classes of motion. A problem arises also in the case of dynamical processes observed visually: background clutter arising for example, in camouflage, produces non-Gaussian observation noise. Even with a single dynamical class, non-Gaussian observations put the learning problem beyond the scope of EM-K. For those cases, we show here how "EM-C"-based on the CONDENSATION algorithm which propagates random "particle-sets," can solve the learning problem. Here, learning in clutter is studied experimentally using visual observations of a hand moving over a desktop. The resulting learned dynamical model is shown to have considerable predictive value: when used as a prior for estimation of motion, the burden of computation in visual observation is significantly reduced. Multiclass dynamics are studied via visually observed juggling; plausible dynamical models have been found to emerge from the learning process, and accurate classification of motion has resulted. In practice, EM-C learning is computationally burdensome and the paper concludes with some discussion of computational complexity.

Some issues in markerless tracking of human body motion are addressed. Extended Kalman filters have commonly been applied to kinematic variables, to combine predictions consistent with plausible motion, with the incoming stream of visual measurements. Kalman filtering is applicable only when the underlying distribution is approximately Gaussian. Often this assumption proves remarkably robust. There are two pervasive circumstances under which the Gaussianity assumption can break down. The first is kinematic singularity and the second is at joint endstops. Failure of Kalman filtering under these circumstances is illustrated. The non-Gaussian nature of the distributions is demonstrated experimentally by means of Monte Carlo simulation. Random simulation (particle filtering or Condensation) proves to provide a robust alternative algorithm for tracking that can also deal with these difficult conditions.

Tracking with deformable contours in a filtering framework requires a dynamical model for prediction. For any given application, tracking is improved by having an accurate model, learned from training data. We develop a method for learning dynamical models from training sequences, explicitly taking account of the fact that training data are noisy measurements and not true states. By introducing an 'augmented-state smoothing filter' we show how the technique of Expectation-Maximisation can be applied to this problem, and show that the resulting algorithm produces more robust and accurate tracking.