Learning to learn: From smart machines to intelligent machines

Image and Vision Computing, 2009

One major goal of the COSPAL project is to develop an artificial cognitive system architecture with the capability of exploratory learning. Exploratory learning is a strategy that allows to apply generalization on a conceptual level, resulting in an extension of competences. Whereas classical learning methods aim at best possible generalization, i.e., concluding from a number of samples of a problem class to the problem class itself, exploration aims at applying acquired competences to a new problem class. Incremental or online learning is an inherent requirement to perform exploratory learning.

AI & SOCIETY, 2018

Will robots ever be able to learn like humans? To answer that question, one first needs to ask: what is learning? Hubert and Stuart Dreyfus had a point when they claimed that computers and robots would never be able to learn like humans because human learning, after an initial phase of rule-based learning, is uncertain, context sensitive and intuitive (Dreyfus and Dreyfus in A five stage model of the mental activities involved in directed skill acquisition.

Spatial Vision, 2000

The problem of learning is arguably at the very core of the problem of intelligence, both biological and arti cial. In this paper we sketch some of our work over the last ten years in the area of supervised learning, focusing on three interlinked directions of research: theory, engineering applications (that is, making intelligent software) and neuroscience(that is, understanding the brain's mechanisms of learning).

Entities that can learn about their environment include natural and artificial systems, acting individually or as a part of a larger group or network. In this article, we speculate whether there might be some simple mechanisms underlying some of the diverse learning strategies observed across many different fields, e.g. biology, psychology, business, machine learning, etc. We present a simple statistical model that can reproduce a wide variety of empirical learning curves, modeling performance as a function of cumulative experience.

The 2011 International Joint Conference on Neural Networks, 2011

Motivated learning (ML) is a new biologically inspired machine learning method. It is the combination of a reinforcement learning (RL) algorithm and a system that creates hierarchy of goals. The goal creation system is concerned with creating new internal goals, building a hierarchy of them, and controlling the agent's behavior according to this constituted hierarchy of goals. As in case of reinforcement learning method, a motivated learning agent is learning through interaction with the environment. The comparisons of both methods in special type test environment show that the motivated learning method is more efficient in learning complex relations between available resources (concepts). ML has better performance than RL, especially in dynamically changing environments. In the presented experiments we have shown that ML based agent, which has the ability to set its internal goals autonomously, is able to fulfill the designer's goals more effectively than RL based agent. In addition, because the observed concepts are not predefined but emerge during the learning process, this method also addresses problem of merging connectionist and symbolic approaches for intelligent autonomous systems.

Artificial General Intelligence Conference, 2019

An important feature of human learning is the ability to continuously accept new information and unify it with existing knowledge, a process that proceeds largely automatically and without catastrophic side-effects. A generally intelligent machine (AGI) should be able to learn a wide range of tasks in a variety of environments. Knowledge acquisition in partially-known and dynamic task-environments cannot happen all-at-once, and AGI-aspiring systems must thus be capable of cumulative learning: efficiently making use of existing knowledge while learning new things, increasing the scope of ability and knowledge incrementally-without catastrophic forgetting or damaging existing skills. Many aspects of such learning have been addressed in artificial intelligence (AI) research, but relatively few examples of cumulative learning have been demonstrated to date and no generally accepted explicit definition exists of this category of learning. Here we provide a general definition of cumulative learning and describe how it relates to other concepts frequently used in the AI literature.

EURASIP Journal on Wireless Communications and Networking, 2012

Cognitive systems were first introduced by Mitola and in the last decade they have proved to be beneficial in selfmanagement functionalities of future generation networks. The advantages and the way that networks gain benefits from cognitive systems is analysed in this article. Moreover, since such systems are closely related to machine learning, the focus of this article is also placed on machine learning techniques applied both in the network and the user devices side. In particular, celebrating 10 years of cognitive systems, this survey-oriented article presents an extended state-of-the-art of machine learning applied to cognitive systems as coming from the recent research and an overview of three different learning capabilities of both the network and the user device.

2012

This paper presents the thesis that all learning agents of finite information size are limited by their informational structure in what goals they can efficiently learn to achieve in a complex environment. Evolutionary change is critical for creating the required structure for all learning agents in any complex environment. The thesis implies that there is no efficient universal learning algorithm. An agent can go past the learning limits imposed by its structure only by slow evolutionary change or blind search which in a very complex environment can only give an agent an inefficient universal learning capability that can work only in evolutionary timescales or improbable luck.

Wolfgang Sachse, Cornell professor of theoretical and applied mechanics, discusses how a neural-like processor can be used to analyze ultrasonic signals in materials testing. Explanation-Based Learning for Machines I 8 A recent development in the field of artificial intelligence is research on machine learning that is deductive in nature and well suited to problem-solving tasks. Alberto Maria Segre, an assistant professor in Cornell's Department of Computer Science, discusses his work in this area.