State of the Art results in Intent Classification using Sematic Hashing for three datasets: AskUbuntu, Chatbot and WebApplication.
-
Updated
May 5, 2020 - Jupyter Notebook
State of the Art results in Intent Classification using Sematic Hashing for three datasets: AskUbuntu, Chatbot and WebApplication.
Semantic Image Similarity Search in Elasticsearch
Semantic Adaptive Hash & Knowledge Seed Engine — compress knowledge into compact semantic seeds for low-RAM AI systems.
Research: can a token's weights be generated from a 64-bit code rather than looked up from a global tensor? Binary activations, shared low-rank basis, 41.6M-param LM.
Give every word a 64-bit semantic fingerprint — one u64, one POPCNT, pure CPU. Recall@10 0.74; scale-stable from 3k to 16k words.
Superseded by odgs-protocol (v6.1.0) — see MetricProvenance/odgs-protocol for the current Apache 2.0 reference engine.
Cross-Modal Semantic Hashing for Zero-Downlink Satellite Constellation Awareness
AI agent and machine-to-machine protocol: canonical state frames, Q-field logic, HMAC seals, HTTP Fabric and conformance tests.
To associate your repository with the semantic-hashing topic, visit your repo's landing page and select "manage topics."