Related papers: Learning From the Past with Cascading Eligibility …

Delayed feedback poses a core challenge for online CVR prediction, forcing a trade-off between label accuracy and data freshness. Existing methods address this through delay modeling or sample reweighting, yet neglect how post-click…

Spiking neural networks implemented in dynamic neuromorphic processors are well suited for spatiotemporal feature detection and learning, for example in ultra low-power embedded intelligence and deep edge applications. Such pattern…

To model time series accurately is important within a wide range of fields. As the world is generally too complex to be modelled exactly, it is often meaningful to assess the probability of a dynamical system to be in a specific state. This…

Stochastic neural networks are a prototypical computational device able to build a probabilistic representation of an ensemble of external stimuli. Building on the relationship between inference and learning, we derive a synaptic plasticity…

Appropriate credit assignment for delay rewards is a fundamental challenge for reinforcement learning. To tackle this problem, we introduce a delay reward calibration paradigm inspired from a classification perspective. We hypothesize that…

Eligibility traces in reinforcement learning are used as a bias-variance trade-off and can often speed up training time by propagating knowledge back over time-steps in a single update. We investigate the use of eligibility traces in…

Deep learning has achieved impressive prediction accuracies in a variety of scientific and industrial domains. However, the nested non-linear feature of deep learning makes the learning highly non-transparent, i.e., it is still unknown how…

Continual learning aims to learn a sequence of tasks from dynamic data distributions. Without accessing to the old training samples, knowledge transfer from the old tasks to each new task is difficult to determine, which might be either…

Many real-world tasks involve delayed effects, where the outcomes of actions emerge after varying time lags. Existing delay-aware reinforcement learning methods often rely on state augmentation, prior knowledge of delay distributions, or…

Real-world applications of neural language models often involve running many different models over the same corpus. The high computational cost of these runs has led to interest in techniques that can reuse the contextualized embeddings…

How can we build agents that keep learning from experience, quickly and efficiently, after their initial training? Here we take inspiration from the main mechanism of learning in biological brains: synaptic plasticity, carefully tuned by…

Representation learning of pedestrian trajectories transforms variable-length timestamp-coordinate tuples of a trajectory into a fixed-length vector representation that summarizes spatiotemporal characteristics. It is a crucial technique to…

Sequential prediction is challenging in regimes of delayed disambiguation, where early observations are ambiguous and multiple latent explanations remain plausible until sufficient evidence accumulates. Standard approaches based on marginal…

Temporal sequences have become pervasive in various real-world applications. Consequently, the volume of data generated in the form of continuous time-event sequence(s) or CTES(s) has increased exponentially in the past few years. Thus, a…

Continual learning aims to enable machine learning models to learn a general solution space for past and future tasks in a sequential manner. Conventional models tend to forget the knowledge of previous tasks while learning a new task, a…

Decomposing knowledge into interchangeable pieces promises a generalization advantage when there are changes in distribution. A learning agent interacting with its environment is likely to be faced with situations requiring novel…

Updating the tracker model with adverse bounding box predictions adds an unavoidable bias term to the learning. This bias term, which we refer to as model decay, offsets the learning and causes tracking drift. While its adverse affect might…

We study the problem of continual test-time adaption where the goal is to adapt a source pre-trained model to a sequence of unlabelled target domains at test time. Existing methods on test-time training suffer from several limitations: (1)…

Meta-learning methods perform well on new within-distribution tasks but often fail when adapting to out-of-distribution target tasks, where transfer from source tasks can induce negative transfer. We propose a causally-aware Bayesian…

A single dynamical system with time-delayed feedback can emulate networks. This property of delay systems made them extremely useful tools for Machine Learning applications. Here we describe several possible setups, which allow emulating…