
Recent Posts
 Comprehension Based Language Modeling
 Cognitive Architectures
 Architectures and Language Instincts
 Why we need a new foundation of mathematics
 The Foundations of Mathematics.
 Friendly AI and the Servant Mission
 AI and Free Will: When do choices exist?
 Metaphor and Mathematics
 Chomsky vs. Hinton
 The Free Lunch Theorem
 Situations
 Tarski and Mentalese
 Wittgenstein and Mentalese
 Vector semantics or Vector Categories
 Grounding
Author Archives: McAllester
Comprehension Based Language Modeling
One of the holy grails of the modern deep learning community is to develop effective methods for unsupervised learning. I have always held out hope that the semantics of English could be learned from raw unlabeled text. The plausibility of a … Continue reading
Posted in Uncategorized
Leave a comment
Cognitive Architectures
Within the deep learning community there is considerable interest in neural architecture. There are convolutional networks, recurrent networks, LSTMs, GRUs, attention mechanisms, highway networks, inception networks, residual networks, fractal networks and many more. Most of these architectures can be viewed as certain feedforward circuit … Continue reading
Posted in Uncategorized
3 Comments
Architectures and Language Instincts
This post is inspired by a recent book and article by Vyvyan Evans declaring the death of the PinkerChomsky notion of a language instinct. I have written previous posts on what I call the ComskyHinton axis of innateknowledge vs. general learning and … Continue reading
Posted in Uncategorized
3 Comments
Why we need a new foundation of mathematics
I just finished what I am confident is the final revision of my paper on the foundations of mathematics. I want to explain here what this is all about. Why do we need a new foundation of mathematics? ZFC set … Continue reading
Posted in Uncategorized
1 Comment
The Foundations of Mathematics.
It seems clear that most everyday human language, and presumably most everyday human thought, is highly metaphorical. Most human statements do not have definite Boolean truth values. Everyday statements have a degree of truth and appropriateness as descriptions of actual … Continue reading
Posted in Uncategorized
Leave a comment
Friendly AI and the Servant Mission
Most computer science academics dismiss any talk of real success in artificial intelligence. I think that a more rational position is that no one can really predict when human level AI will be achieved. John McCarthy once told me that … Continue reading
Posted in Uncategorized
7 Comments
AI and Free Will: When do choices exist?
This post was originally made on July 15, 2013. This is a philosophical post instigated by Scott Aaronson’s recent paper and blog post regarding free will. A lot hinges, I think, on how one phrases the question. I like the question … Continue reading
Posted in Uncategorized
4 Comments