Learning | EPFL Graph Search

Learning is the process of acquiring new understanding, knowledge, behaviors, skills, values, attitudes, and preferences. The ability to learn is possessed by humans, animals, and some machines; there is also evidence for some kind of learning in certain plants. Some learning is immediate, induced by a single event (e.g. being burned by a hot stove), but much skill and knowledge accumulate from repeated experiences. The changes induced by learning often last a lifetime, and it is hard to distinguish learned material that seems to be "lost" from that which cannot be retrieved. Human learning starts at birth (it might even start before in terms of an embryo's need for both interaction with, and freedom within its environment within the womb.) and continues until death as a consequence of ongoing interactions between people and their environment. The nature and processes involved in learning are studied in many established fields (including educational psychology, neuropsychology, exp

Learning strategies and representations for intuitive robot learning from demonstration

Thibaut Antoine Kulak

Robots are becoming more and more present around us, both in industries and in our homes. One key capability of robots is their adaptability to various situations that might appear in the real world. Robot skill learning is therefore a crucial aspect of robotics aiming to provide robots with programs enabling them to perform one or several tasks successfully. While such programming is usually done by an engineer or a developer, making robot programming available to anyone would dramatically increase the range of applications currently feasible for robots. Learning from Demonstration (LfD) is a robot skill learning paradigm addressing this aim by developing intuitive frameworks for non-expert users to easily (re)program robots. While Learning from Demonstration has emerged as a successful way to program robots, several limitations remain to be addressed. Typical approaches still require some forms of preprocessing, such as the alignment of the demonstrations, or the choice of the movement representation. Also, the algorithms have to run with a relatively low number of demonstrations that human users are typically willing to give, while being performant, adaptable and generalizable to new situations. In this thesis, we propose to address these shortcomings with methods that make Learning from Demonstration more intuitive and user-friendly. We notably propose a novel movement representation requiring no demonstration alignment, and active learning strategies that permit to learn complex skills from fewer demonstrations.

EPFL2021

Introducing Productive Engagement for Social Robots Supporting Learning

Jauwairia Nasir

We have all been one such student or seen such students who can maintain the 'good student' image while playing a video game under the table or those loyal backbenchers, seemingly always distracted, who then ace their exams. These intricacies of human behaviors are just a few examples of what makes it non-trivial and challenging even for expert teachers to know how students' visible behaviors relate with learning. As research investigates ways in which robots and AI can support teachers and students, it is faced with the same challenge of inferring students' engagement; thus, making the investigation of this topic increasingly popular in educational HRI. The state of the art usually explores the relationship between the robot behaviors and the engagement state of the learner while assuming a linear relationship between engagement and learning. However, is it correct to assume that to maximize learning, one needs to maximize engagement? Furthermore, conventional supervised engagement models require human annotators to get labels. This not only is laborious but can also introduce subjectivity. Can we have machine-learning engagement models where annotations do not rely on human annotators? Additionally, with the increase in open-ended learning activities which by design employ the 'learning by failing' paradigm, in-task performance can not be the best measure for learning. Can we instead rely on multi-modal behaviors? In an effort to cater for these challenges, this thesis dives deep to identify and quantify the relationship between learning and engagement, which we term as Productive Engagement (PE). In order to develop, design, and evaluate our PE framework, (1) we first designed and developed an open-ended collaborative learning activity that served as a platform for evaluating different robot variants over time. With 98 children interacting with the baseline version from 2 international Swiss schools, we showed that in-task performance and learning are indeed not correlated. Thus, this showed the importance of not being limited to robot interventions that affect only superficial measures of students' learning. (2) Then, with learner's multi-modal behaviors, we showed that indeed there is a hidden link between learner's behaviors and learning that can be quantified, i.e., validating the proposed concept of Productive Engagement. (3) This quantifiable link surfaced three collaborative multi-modal learner profiles, by using a forward and backward clustering and classification technique, two of which are linked to higher learning. This technique gave a possibility to surface data driven labels for engagement; thus, evading the process of human annotations. We then identified similarities and differences between these learner profiles both at an aggregate and at the temporal level. (4) Based on (3), we constructed a PE score that can either be directly used as an assessment metric by a social robot in real-time or as data driven labels for building more sophisticated regression models. (5) With the learner profiles and the PE score, we designed and evaluated more advanced robot variants for the final studies with ~160 students from 7 international Swiss schools. With the design of different robot variants that employ knowledge about the learner's skills conducive to learning, rather than domain knowledge, in order to provide interventions; we provided a complementary perspective on the role of social robots in educational settings.

EPFL2022

Theory of representation learning in cortical neural networks

Carlos Stein Naves de Brito

Our brain continuously self-organizes to construct and maintain an internal representation of the world based on the information arriving through sensory stimuli. Remarkably, cortical areas related to different sensory modalities appear to share the same functional unit, the neuron, and develop through the same learning mechanism, synaptic plasticity. It motivates the conjecture of a unifying theory to explain cortical representational learning across sensory modalities. In this thesis we present theories and computational models of learning and optimization in neural networks, postulating functional properties of synaptic plasticity that support the apparent universal learning capacity of cortical networks. In the past decades, a variety of theories and models have been proposed to describe receptive field formation in sensory areas. They include normative models such as sparse coding, and bottom-up models such as spike-timing dependent plasticity. We bring together candidate explanations by demonstrating that in fact a single principle is sufficient to explain receptive field development. First, we show that many representative models of sensory development are in fact implementing variations of a common principle: nonlinear Hebbian learning. Second, we reveal that nonlinear Hebbian learning is sufficient for receptive field formation through sensory inputs. A surprising result is that our findings are independent of specific details, and allow for robust predictions of the learned receptive fields. Thus nonlinear Hebbian learning and natural statistics can account for many aspects of receptive field formation across models and sensory modalities. The Hebbian learning theory substantiates that synaptic plasticity can be interpreted as an optimization procedure, implementing stochastic gradient descent. In stochastic gradient descent inputs arrive sequentially, as in sensory streams. However, individual data samples have very little information about the correct learning signal, and it becomes a fundamental problem to know how many samples are required for reliable synaptic changes. Through estimation theory, we develop a novel adaptive learning rate model, that adapts the magnitude of synaptic changes based on the statistics of the learning signal, enabling an optimal use of data samples. Our model has a simple implementation and demonstrates improved learning speed, making this a promising candidate for large artificial neural network applications. The model also makes predictions on how cortical plasticity may modulate synaptic plasticity for optimal learning. The optimal sampling size for reliable learning allows us to estimate optimal learning times for a given model. We apply this theory to derive analytical bounds on times for the optimization of synaptic connections. First, we show this optimization problem to have exponentially many saddle-nodes, which lead to small gradients and slow learning. Second, we show that the number of input synapses to a neuron modulates the magnitude of the initial gradient, determining the duration of learning. Our final result reveals that the learning duration increases supra-linearly with the number of synapses, suggesting an effective limit on synaptic connections and receptive field sizes in developing neural networks.