Related papers: Enhancing Biologically Inspired Hierarchical Tempo…
Cortical Learning Algorithms based on the Hierarchical Temporal Memory, HTM have been developed by Numenta Incorporation from which variations and modifications are currently being investigated upon. HTM offers better promises as a future…
This paper presents a novel approach to address the challenge of online sequence learning for decision making under uncertainty in non-stationary, partially observable environments. The proposed algorithm, Distributed Hebbian Temporal…
In this paper, we propose and investigate a novel memory architecture for neural networks called Hierarchical Attentive Memory (HAM). It is based on a binary tree with leaves corresponding to memory cells. This allows HAM to perform memory…
Long-term conversational large language model (LLM) agents require memory systems that can recover relevant evidence from historical interactions without overwhelming the answer stage with irrelevant context. However, existing memory…
Hierarchical Temporal Memory (HTM) is a biologically inspired machine intelligence technology that mimics the architecture and processes of the neocortex. In this white paper we describe how to encode data as Sparse Distributed…
Recommender systems that can learn from cross-session data to dynamically predict the next item a user will choose are crucial for online platforms. However, existing approaches often use out-of-the-box sequence models which are limited by…
Long-term memory is one of the key factors influencing the reasoning capabilities of Large Language Model Agents (LLM Agents). Incorporating a memory mechanism that effectively integrates past interactions can significantly enhance…
Hyperdimensional computing (HDC) is an emerging computational framework inspired by the brain that operates on vectors with thousands of dimensions to emulate cognition. Unlike conventional computational frameworks that operate on numbers,…
Hardware Transactional Memory (HTM) allows lock-free programming as easy as with traditional coarse-grain locks or similar, while benefiting from the performance advantages of fine-grained locking. Many HTM implementations have been…
High-performance GPU kernels are essential for efficient LLM deployment, yet optimizing them remains expertise-intensive. Recent LLM-based code generation makes automatic GPU operator generation promising, but operator optimization remains…
Hierarchical Temporal Memory (HTM) is a neuromorphic algorithm that emulates sparsity, hierarchy and modularity resembling the working principles of neocortex. Feature encoding is an important step to create sparse binary patterns. This…
Although long-term memory systems have made substantial progress in recent years, they still exhibit clear limitations in adaptability, scalability, and self-evolution under continuous interaction settings. Inspired by cognitive theories,…
Natural spatiotemporal processes can be highly non-stationary in many ways, e.g. the low-level non-stationarity such as spatial correlations or temporal dependencies of local pixel values; and the high-level variations such as the…
Transformer-based models show their effectiveness across multiple domains and tasks. The self-attention allows to combine information from all sequence elements into context-aware representations. However, global and local information has…
Hierarchical temporal memory (HTM) is a biomimetic sequence memory algorithm that holds promise for invariant representations of spatial and spatiotemporal inputs. This paper presents a comprehensive neuromemristive crossbar architecture…
Neuromorphic systems that learn and predict from streaming inputs hold significant promise in pervasive edge computing and its applications. In this paper, a neuromorphic system that processes spatio-temporal information on the edge is…
This paper presents a hetero-associative sequential memory system for mobile manipulators that learns compact, neuromorphic bindings between robot joint states and tactile observations to produce step-wise action decisions with low compute…
Human brains are known to be capable of speeding up visual recognition of repeatedly presented objects through faster memory encoding and accessing procedures on activated neurons. For the first time, we borrow and distill such a capability…
We propose Atomic Active Messages (AAM), a mechanism that accelerates irregular graph computations on both shared- and distributed-memory machines. The key idea behind AAM is that hardware transactional memory (HTM) can be used for simple…
We investigate a new method to augment recurrent neural networks with extra memory without increasing the number of network parameters. The system has an associative memory based on complex-valued vectors and is closely related to…