Learning Evolution: a Survey

Learning is the process of gaining knowledge and implementing this knowledge on behavior. The concept of learning is not strict to just human being, it expanded to include machine also. Now the machines can behave based on the gained knowledge learned from the environment. The learning process is evolving in both human and machine, to keep up with the technology in the world, the human learning evolved into micro-learning and the machine learning evolved to deep learning. In this paper, the evolution of learning is discussed as a formal survey accomplished with the foundation of machine learning and its evolved version of learning which is deep learning and micro-learning as a new learning technology can be implemented on human and machine learning. A procedural comparison is achieved to declare the purpose of this survey, also a related discussion integrates the aim of this study. Finally a concluded points are illustrated as outcome which summarized the practical evolution intervals of the machine learning different concepts.

Human learning follows the dynamics of gradient descent

Artificial neural networks (ANNs) have achieved near human-level performance on many tasks and can account for human behavioural and brain measures in a number of domains. Although a principal strength of ANNs is learning representations from experience, only a handful of contributions have evaluated this process to ask whether ANN learning dynamics provide a good model of human learning. We investigated whether humans learn similarly to an ANN, which adjusts its representations through gradient descent. Gradient descent learning is steep at first and initially ignores covariance between features. ANNs can theoretically display a non-monotonic behaviour in which early in learning, multiple weak predictors determine the ANN’s decision whereas late in learning a single strong predictor can dominate. This initial behaviour was confirmed in a simple ANN and in half of human participants performing a comparable task. Later in gradient descent learning, the ANN changed to placing a greater weight on the stronger predictor, and humans also shifted their preferences in the same way. Hidden Markov modelling of the behaviour of ANNs and humans predicted similar transitions from weak-feature to strong-feature states. Our results suggest a significant proportion of people learn about categories in a manner analogous to ANNs, possibly by updating their mental representations by a process akin to gradient descent. Our findings demonstrate how ANNs can be used to not only explain the products of human learning but also the process.

Human learning follows the dynamics of gradient descent

Artificial neural networks (ANNs) have achieved near human-level performance on many tasks and can account for human behavioural and brain measures in a number of domains. Although a principal strength of ANNs is learning representations from experience, only a handful of contributions have evaluated this process to ask whether ANN learning dynamics provide a good model of human learning. We investigated whether humans learn similarly to an ANN, which adjusts its representations through gradient descent. Gradient descent learning is steep at first and initially ignores covariance between features. ANNs can theoretically display a non-monotonic behaviour in which early in learning, multiple weak predictors determine the ANN’s decision whereas late in learning a single strong predictor can dominate. This initial behaviour was confirmed in a simple ANN and in half of human participants performing a comparable task. Later in gradient descent learning, the ANN changed to placing a greater weight on the stronger predictor, and humans also shifted their preferences in the same way. Hidden Markov modelling of the behaviour of ANNs and humans predicted similar transitions from weak-feature to strong-feature states. Our results suggest a significant proportion of people learn about categories in a manner analogous to ANNs, possibly by updating their mental representations by a process akin to gradient descent. Our findings demonstrate how ANNs can be used to not only explain the products of human learning but also the process.

Object-Based Trace Model for Automatic Indicator Computation in the Human Learning Environments

This paper proposes a traces model in the form of an object or class model (in the UML sense) which allows the automatic calculation of indicators of various kinds and independently of the computer environment for human learning (CEHL). The model is based on the establishment of a trace-based system that encompasses all the logic of traces collecting and indicators calculation. It is im-plemented in the form of a trace database. It is an important contribution in the field of the exploitation of the traces of apprenticeship in a CEHL because it pro-vides a general formalism for modeling the traces and allowing the calculation of several indicators at the same time. Also, with the inclusion of calculated indica-tors as potential learning traces, our model provides a formalism for classifying the various indicators in the form of inheritance relationships, which promotes the reuse of indicators already calculated. Economically, the model can allow organi-zations with different learning platforms to invest only in one traces Management System. At the social level, it can allow a better sharing of trace databases be-tween the various research institutions in the field of CEHL.

The influence of personality features in choosing the profession

A profession or trade is a permanent occupation, an activity based on specialized education that someone regularly pursues on the basis of an appropriate qualification, in order to obtain remuneration. Personality is a universe that constantly encourages knowledge, but which can never be exhausted. Goethe believed that the supreme performance of scientific knowledge is the knowledge of man. The idea is justified both by the maximum complexity of the human being and by the fact that "man represents the supreme value for man." Between Nietzsche's pessimism, which states that "man is the animal that can never be defined," and Protagoras' axiological view, that "man is the measure of all things," personality is a global concept, a structure that cannot be defined only by its structural elements. The concept of interest and its implications for human learning and development have an important role in both education and psychology. In a society that continues to transform, social, economic and psychological factors cause profound changes in the sphere of professions and occupations. Therefore, there must be a transition to a training school and an appropriate way so that anyone can meet the requirements in a constantly changing society.

Reimagining American education: Possible futures: A curriculum that promotes civic ends and meets developmental needs

If schools are to prepare students to participate more productively in civic life, schools will need to ensure that they have opportunities to practice the skills of civic reasoning, argues Carol Lee. Yet schools are challenged by the limits in the curriculum and the difficulty of addressing the different types of prior knowledge that students bring to the classroom. Lee suggests that when schools build their content and pedagogy on current understandings of human learning, they will be better able to enable students from all backgrounds to practice building the understandings they need, now and in the future.

The human learning process in the organizational context

This article, elaborated through bibliographic research, has as a fundamental question the way individuals learn and interact in the context of organizations. Aiming to address how individual learning contributes to organizational learning among individuals. From the literature analyzed, it was found that the knowledge and knowledge acquired individually by people must be added to the communication, interaction and sharing skills with colleagues, within the scope of organizations, so that together they learn the culture, internal system, objectives and practices inherent to it, in order to achieve the existing goals.

Systematic human learning by literature and data mining for feature selection in machine learning

We proposed a learning algorithm for human to conduct literature and data mining for causal factor discovery. The applicability is to select features for a machine learning prediction model, including but not limited to that using real-world, time-varying data from electronic health records. This protocol is relatively quick to find potentially actionable predictors for a clinical prediction while dealing with high dimensionality in big data. However, this protocol might not find a potentially novel cause, since this only exhaustively examines the existing evidences in a single study. The key stages consisted of systematic human learning, causal diagram construction, data preprocessing, causal inference modeling, and development and validation of a prediction model to describe the explainability.

Fuzzy-Based EOQ Model With Credit Financing and Backorders Under Human Learning

In this paper, an inventory model has been developed with trade credit financing and back orders under human learning. In this model, it is considered that the seller provides a credit period to his buyer to settle the account and the buyer accepts the credit period policy with certain terms and conditions. The impact of learning and credit financing on the size of the lot and the corresponding cost has been presented. For the development of the model, demand and lead times have been taken as the fuzzy triangular numbers are fuzzified, and then learning has been done in the fuzzy numbers. First of all, the consideration of constant fuzziness is relaxed, and then the concept of learning in fuzzy under credit financing is joined with the representation, assuming that the degree of fuzziness reduces over the planning horizon. Finally, the expected total fuzzy cost function is minimized with respect to order quantity and number of shipments under credit financing and learning effect. Lastly, sensitive analysis has been presented as a consequence of some numerical examples.