We observe the success of artificial neural networks in simulating human performance on a number of tasks: such as image recognition, natural language processing, etc. However, there are limits to state-of-the- art AI that separate it from human-like intelligence. Humans can learn a new skill without forgetting what they have already learned and they can improve their activity and gradually become better learners. Today’s AI algorithms are limited in how much previous knowledge they are able to keep through each new training phase and how much they can reuse. In practice this means that it is necessary to build and adjust new algorithms to every new particular task. This is closer to a sophisticated data processing than to real intelligence. This is why research concerning generalisation are becoming increasingly important. A generalization in AI means that system can generate new compositions or find solutions for new tasks that are not present in the training corpus. General Neural Model and intelligent agent should have very general learning capabilities, should not just be able to memorize the solution to a fixed set of tasks during creating of stories, but learn how to generalize to new problems it encounters. It can generalize problem in the sens that solving one or more of tasks should make solving other task easier. There is domain called Meta-learning where will be possible to find solutions for this problems. Meta-learning describes research that aims to create machines capable of general intelligent action. “General” means that one AI program realizes number of different tasks and learn to learn by transforming machine learning algorithms. We must focus on self-improvement techniques e.g. Reinforcement Learning and integrate it with deep learning, recurrent networks, etc.