Jeremy London
jeremy-london
AI & ML interests
LSTM, Multimodal AI, synthetic dataset generation, fine-tuning Large Language Models (LLM) for agent tasks, knowledge graphs, system-level AI opportunities, recommendation systems, feature extraction, classification, embedding searches, NER (Named Entity Recognition), generative modeling
Recent Activity
liked
a model
13 days ago
alibaba-damo/mgp-str-base
Reacted to
TuringsSolutions's
post
with 👍
about 2 months ago
Neural Network Chaos Monkey: Randomly shuts off parts of the neural network during training. The Chaos Monkey is super present at Epoch 1, is gone by the final Epoch. My hypothesis was that this would either increase the robustness of the model, or it would make the outputs totally worse. You can 100% reproduce my results, chaos wins again.
https://youtu.be/bWA9unotJ7k
upvoted
a
collection
about 2 months ago
GLiClass
Organizations
jeremy-london's activity
No public activity