In spite of the amazing results obtained by deep learning in many applications, intelligent agents acting in a complex environment can strongly benefit from prior knowledge on the environment, especially when it is expressed by logic formalisms. In this brief course, we give an introduction to deep learning and then we introduce a theory for modeling the agent interactions with the environments by means of the unified notion of constraint, that is shown to embrace machine learning and logic inferential processes within the same mathematical framework. Then, we present LYRICS (Learning Yourself Reasoning and Inference with ConstraintS), which can be regarded as a tool to assist the design of intelligent agents in a rich variety of application domains. LYRICS is implemented in TersorFlow (TF) and provides an input language to define arbitrary First Order Logic background knowledge, including clauses, groundings, and constants. The predicates and the functions can be bound to any TF computational graph, while the formulas are converted into a set of real-valued constraints by means of t-norms, that can be defined during the design. As a result, we end up into a unified framework for performing learning and inference that is especially useful when both data and structured knowledge are jointly available. A number of cases studies are illustrated to facilitate the acquisition of the theory.

Introduction to machine learning and neural networks.

**4 February 9.00-13.00.** Aula B0.3

Deep networks and Backpropagation.

**5 February 9.00-13.00.** Aula B0.3

Convolutional nets, recurrent and graphical networks.

**6 February 9.00-13.00.** Aula B0.3

Learning with constraints.

**7 February 9.00-13.00.** Aula B0.3

Bridging logic and learning.

**8 February 9.00-13.00.** Aula B0.3

Info: Prof. Alfonso GEREVINI

Dip. Ingegneria dell’Informazione