Epstein Secrets

e we describe in detail the strategy that would be used to integrate 129 EFTA00624276 130 26 Perceptual and Motor Hierarchies CogPrime with the DeSTIN framework for AGI perception/action (which was described in some detail in Chapter 4 of Part 1). In terms of the integrative cognitive architecture

ogPrime's action selection aspect is fairly similar to MicroPsi (due to the common foundation in Dorner's Psi model), the dynamics are less similar. MicroPsi's dynamics are a little closer to being a formal neural net model, whereas ECAN's economic foundation tends to push it in different directions. The

s some simple simulated financial mechanisms, building on the economic metaphor of ELAN, that are different from, and more complex than, anything in MicroPsi. The main actors (apart from the usual ones like the AtomTable, economic attention alloca- tion, etc.) in the tale to be told here are as follows:

spatiotemporally hier- archical deep learning system is an effective way to handle representation and learning of low-level sensorimotor knowledge. DeSTIN is one example of a deep learning system of this nature that can be effective in this context. i. One effective way to handle goals is to represent

ion and intelligence. It has been tested on some practical control applications, and also on simulating artificial agents in a simple virtual world. MicroPsi's comprehen- siveness and basis in neuroscience and psychology are impressive, but in the current version of MicroPsi, learning and reasoning are ca

nts in a simple virtual world. MicroPsi's comprehen- siveness and basis in neuroscience and psychology are impressive, but in the current version of MicroPsi, learning and reasoning are carried out by algorithms that seem unlikely to scale. OCP incorporates the Psi model for motivation and emotion, so tha

a spatiotemporally hier- archical deep learning system is an effective way to handle representation and learning of low-level sensorimotor knowledge. DeSTIN is one example of a deep learning system of this nature that can be effective in this context. i. One effective way to handle goals is to represent

tion and intelligence. It has been tested on some practical control applications, and also on simulating artificial agents in a simple virtual world. MicroPsi’s comprehen- siveness and basis in neuroscience and psychology are impressive, but in the current version of MicroPsi, learning and reasoning are car

ents in a simple virtual world. MicroPsi’s comprehen- siveness and basis in neuroscience and psychology are impressive, but in the current version of MicroPsi, learning and reasoning are carried out by algorithms that seem unlikely to scale. OCP incorporates the Psi model for motivation and emotion, so that

. PLN, a probabilistic logic engine; MOSES, an evolutionary program learning algorithm; ECAN, a nonlinear-dynamical attention allocation framework; DeSTIN, a deep learning perception algorithm) within a human-like cognitive architecture. The integration of these multiple learning algorithms is achieved

e more attention. Action selection will be done via OpenPsi according to the Psi model, roughly similarly to how it is done in Joscha Bach's (2012) MicroPsi model. This means that actions will be chosen based on the probabilities with which they are estimated to lead to achievement of the currently high-

. PLN, a probabilistic logic engine; MOSES, an evolutionary program learning algorithm; ECAN, a nonlinear-dynamical attention allocation framework; DeSTIN, a deep learning perception algorithm) within a human-like cognitive architecture. The integration of these multiple learning algorithms is achieved

e more attention. Action selection will be done via OpenPsi according to the Psi model, roughly similarly to how it is done in Joscha Bach's (2012) MicroPsi model. This means that actions will be chosen based on the probabilities with which they are estimated to lead to achievement of the currently high-

c, cognitive and linguistic functions. We will achieve this via the creation and real-time utilization of links between the nodes in CogPrime's and DeSTIN's internal networks (a topic to be explored in more depth Inter in this chapter). 6.4 Memory Types and Associated Cognitive Processes in CogPrime

ut on the big- picture level the main difference lies in the way the cognitive synergy principle is pursued in the two different approaches. Psi and MicroPsi rely on very simple learning algorithms that are closely tied to the "quad" neurosymbolic knowledge representation, and hence interoperate in a fai

ric, cognitive and linguistic functions. We will achieve this via the creation and real-time utilization of links between the nodes in CogPrime’s and DeSTIN’s internal networks (a topic to be explored in more depth later in this chapter). 6.4 Memory Types and Associated Cognitive Processes in CogPrime N

but on the big- picture level the main difference lies in the way the cognitive synergy principle is pursued in the two different approaches. Psi and MicroPsi rely on very simple learning algorithms that are closely tied to the “quad” neurosymbolic knowledge representation, and hence interoperate in a fairl