Category: System 2 AI
-
Inductive Biases
“”” Inductive bias refers to the set of assumptions that a learner (human or machine) makes to predict outputs for previously unseen inputs when trying to learn from a given set of training examples. In other words, it’s the bias or set of preferences a learning algorithm has when inferring a hypothesis or function from…
-
Dual process theory and key questions in SOTA DL
As I understood more about how Type 1 / Type 2 processing is defined and what the Global Workspace Theory for consciousness is about. I came to realized while Type 2 cognitive processing and consciousness explained by GWT share a striking similarity, namely, they both require the working memory to hold and process elements coming…
-
World Model
Bengio’s world model Bengio’s concept of world model is a generative model that learns the abstract structure, or abstraction, of x. And this is similar to how human learns and understands the world. This is powerful because this enables training with far less data (because we don’t operate at the low level anymore) and better…
-
GWT – Global Workspace Theory
What is it? Global Workspace Theory (GWT) is a cognitive architecture and theory of consciousness proposed by psychologist Bernard Baars. This theory is often used to explain various aspects of human cognition, including attention, perception, and action. The central metaphor of GWT is a “theater of consciousness.” In this theater, the conscious mind is like…
-
GFlowNets study notes
GFlowNet is really MANY THINGS IN ONE THING. And I need to put all aspects together in order to fully understand it. Like, how is this a stochastic policy in the light of it being a generative model i.e., P(y,x)? Generative active learning, reinforcement learning, stochastic policy, generative model, energy-based probabilistic modelling, variational models and…
-
How do GFlowNets relate to attention or human thinking?
How is that related to attention? It makes sense to consider deterministic transitions when the policy is an internal policy, not operating in some stochastic external environment, but instead performing computational choices (like what to attend to, what computation to perform, what memory to retrieve, etc). Immediately, GFlowNets are motivated by the kind of internal…
-
AI study blog 1
In Yoshua’s blog post introducing the GFlowNets, most concepts used to describe the new framework are something I don’t know. So, the first phase is to understand all basic concepts:
Gang Fang's Blog 