Related papers: Influence-aware Memory Architectures for Deep Rein…
To sustain coherent long-term interactions, Large Language Model (LLM) agents must navigate the tension between acquiring new information and retaining prior knowledge. Current unified stream-based memory systems facilitate context updates…
A key attribute that drives the unprecedented success of modern Recurrent Neural Networks (RNNs) on learning tasks which involve sequential data, is their ability to model intricate long-term temporal dependencies. However, a well…
Many living and artificial systems improve their fitness or performance by adapting to changing environments or diverse training data. However, it remains unclear how such environmental variation influences adaptation, what is learned in…
Complex nonlinear dynamics are ubiquitous in many fields. Moreover, we rarely have access to all of the relevant state variables governing the dynamics. Delay embedding allows us, in principle, to account for unobserved state variables.…
Memory models such as Recurrent Neural Networks (RNNs) and Transformers address Partially Observable Markov Decision Processes (POMDPs) by mapping trajectories to latent Markov states. Neither model scales particularly well to long…
Recurrent neural networks can learn complex transduction problems that require maintaining and actively exploiting a memory of their inputs. Such models traditionally consider memory and input-output functionalities indissolubly entangled.…
Anticipating future actions based on spatiotemporal observations is essential in video understanding and predictive computer vision. Moreover, a model capable of anticipating the future has important applications, it can benefit…
As deep reinforcement learning driven by visual perception becomes more widely used there is a growing need to better understand and probe the learned agents. Understanding the decision making process and its relationship to visual inputs…
Neural networks allow Q-learning reinforcement learning agents such as deep Q-networks (DQN) to approximate complex mappings from state spaces to value functions. However, this also brings drawbacks when compared to other function…
Contemporary wisdom based on empirical studies suggests that standard recurrent neural networks (RNNs) do not perform well on tasks requiring long-term memory. However, precise reasoning for this behavior is still unknown. This paper…
Reason and inference require process as well as memory skills by humans. Neural networks are able to process tasks like image recognition (better than humans) but in memory aspects are still limited (by attention mechanism, size). Recurrent…
The key challenge of sequence representation learning is to capture the long-range temporal dependencies. Typical methods for supervised sequence representation learning are built upon recurrent neural networks to capture temporal…
Continual learning is considered a promising step towards next-generation Artificial Intelligence (AI), where deep neural networks (DNNs) make decisions by continuously learning a sequence of different tasks akin to human learning…
Recently, analog compute-in-memory (CIM) architectures based on emerging analog non-volatile memory (NVM) technologies have been explored for deep neural networks (DNN) to improve energy efficiency. Such architectures, however, leverage…
The self-attention mechanism has emerged as a critical component for improving the performance of various backbone neural networks. However, current mainstream approaches individually incorporate newly designed self-attention modules (SAMs)…
In supervised machine learning, an agent is typically trained once and then deployed. While this works well for static settings, robots often operate in changing environments and must quickly learn new things from data streams. In this…
Simultaneous localization and mapping (SLAM) with implicit neural representations has received extensive attention due to the expressive representation power and the innovative paradigm of continual learning. However, deploying such a…
The powerful learning ability of deep neural networks enables reinforcement learning agents to learn competent control policies directly from continuous environments. In theory, to achieve stable performance, neural networks assume i.i.d.…
Real-world time series data exhibit non-stationary behavior, regime shifts, and temporally varying noise (heteroscedastic) that degrade the robustness of standard regression models. We introduce the Variability-Aware Recursive Neural…
Data-centric learning emphasizes curating high-quality training samples to boost performance rather than designing new architectures. A central problem is to estimate the influence of training sample efficiently. Prior studies largely focus…