understanding-ai
understanding-ai copied to clipboard
flrngel
personal repository
# Abstract - quantum probability theory - quantum-inspired LMs have two limitations - not taken into account interaction among the words with multiple meanings - lacking theoretical foundation accounting for...
https://arxiv.org/abs/1806.05635 # Abstract - `SIL(Self Imitation Learning)` is to verify past good experiences can indirectly drive deep exploration. - competitive to state-of-the-art # 1. Introduction - Atari "Montezuma's Revenge" -...
http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.66.5667&rep=rep1&type=pdf # 1. Introduction - In text domain, there is excessive number of features - To control sparsity, "threshold to cut-off feature" was used traditionally - This paper suggests that...
https://arxiv.org/abs/1609.04938 # 1. Abstract - this model is end-to-end - model uses convolutional network and recurrent network - current models achieve 25% accuracy, but paper model achieves 75% accuracy #...
https://arxiv.org/abs/1806.02847 google brain # Abstract - paper's model outperforms previous state-of-the-art methods in [Winograd Schema challenges](https://en.wikipedia.org/wiki/Winograd_Schema_Challenge) - paper model uses large ***RNN Language Model*** # 1. Introduction - previous models...
https://arxiv.org/abs/1806.01822 Paper from Deepmind # Abstract - paper's model built with intuition - so it is unclear why this works well - shows state-of-the-art on the WikiText103, Project Gutenberg, and...
https://arxiv.org/abs/1612.08083 # Abstract - propose gating mechanism - uses [WikiText-103](https://einstein.ai/research/the-wikitext-long-term-dependency-language-modeling-dataset) and [Google Billion Words](https://github.com/ciprian-chelba/1-billion-word-language-modeling-benchmark) - proposed model is very competitive to strong recurrent models on large scale language tasks #...
https://arxiv.org/abs/1801.10198 published as a conference paper at ICLR 2018 # Abstract - This model uses decoder-only architecture which is modified from Transformer - Evaluation uses perplexity, ROUGE, human evaluations #...
https://arxiv.org/abs/1702.02390 # Abstract - this model uses rnn + feed-forward convolutional architecture - author claims this model has - fast train convergence - handles long sequences - avoid major difficulties...
https://arxiv.org/abs/1802.06070 # Abstract - Learn **skills** by maximizing information using maximum entropy policy - Train typical reinforcement learning with best **skill** after unsupervised learning # 1. Introduction - **Skill** is...