- The Meaning is The Use.
- The Mental States of Language Models
- GPT-3 Semantic Parsing with Simple Sentence Graphs
- The Case Against Grounding
- Quo Vadis Language Model? Will I ever be able to trust you?
- Encoder Autonomy
- Reinterpreting AlphaZero
- Commonsense and Language Models
- A Consistency Theorem for BERT
- The Inevitability of Vector Quantization in Deep Architectures
- Thoughts from TTIC31230: Rate-Distortion Metrics for GANs.
- Thoughts from TTIC31230: Rethinking Generalization.
- Thoughts from TTIC31230: Langevin Dynamics and the Struggle for the Soul of SGD.
- Thoughts from TTIC31230: Hyperparameter Conjugacy
- Superintelligence and The Truth
- Predictive Coding and Mutual Information
- RL and the Game of Mathematics
- The Role of Theory in Deep Learning
- Choice as a Natural Kind Term
- CTC and the EG Algotithm: Discrete Latent Choices without Reinforcement Learning
Daily Archives: April 17, 2019
Thoughts from TTIC31230: Rate-Distortion Metrics for GANs.
Throughout my career I have believed that progress in AI arises from objective evaluation metrics. When I first learned of GANs I was immediately skeptical because of the apparent lack of meaningful metrics. While GANs have made enormous progress in … Continue reading
Posted in Uncategorized Leave a comment