Recent approaches to human concept learning have successfully combined the power of symbolic, infinitely productive, rule systems and statistical learning. The aim of most of these studies is to reveal the underlying language structuring these representations and providing a general substrate for thought. Here, we ask about the plasticity of symbolic descriptive languages. We perform two concept learning experiments, that consistently demonstrate that humans can change very rapidly the repertoire of symbols they use to identify concepts, by compiling expressions which are frequently used into new symbols of the language. The pattern of concept learning times is accurately described by a Bayesian agent that rationally updates the probability of compiling a new expression according to how useful it has been to compress concepts so far. By portraying the Language of Thought as a flexible system of rules, we also highlight the intrinsic difficulties to pin it down empirically. Keywords: Language of Thought, Concept Learning, Probabilistic Inference 1. Introduction How can children acquire a vast universe of concepts with seemingly very little exposure? Preprint submitted to Cognitive Psychology. Combinatorial languages can describe a vast set of concepts from a small set of primitives. This can be understood in a relatively simple example in the domain of shapes. A combinatorial and symbolic language similar to Logo [5] can combine operations such as "move", "pen up", "pen down" or "rotate" to generate an infinite set of expressions (or programs) which, when evaluated, can convey all sort of shapes.

About this course: This course describes Bayesian statistics, in which one's inferences about parameters or hypotheses are updated as evidence accumulates. You will learn to use Bayes' rule to transform prior probabilities into posterior probabilities, and be introduced to the underlying theory and perspective of the Bayesian paradigm. The course will apply Bayesian methods to several practical problems, to show end-to-end Bayesian analyses that move from framing the question to building models to eliciting prior probabilities to implementing in R (free statistical software) the final posterior distribution. Additionally, the course will introduce credible regions, Bayesian comparisons of means and proportions, Bayesian regression and inference using multiple models, and discussion of Bayesian prediction. We assume learners in this course have background knowledge equivalent to what is covered in the earlier three courses in this specialization: "Introduction to Probability and Data," "Inferential Statistics," and "Linear Regression and Modeling."

One of the largest growing demographics in the EU is individuals aged 65 and over, and two thirds of this group are in situation of multimorbidity, i.e., perons who suffer from two or more chronic diseases. The ineffective treatment of multimorbidity has been pointed out as an urgent problem to address by the Academy of Medical Sciences in a recently released report. As part of an EU H2020 funded project called ProACT, our team at IBM Research – Ireland is working with partners in academia and industry to find new ways to use IoT, AI and cloud technologies to advance self-management capabilities and home-based integrated care for Persons with Multimorbidity (PwM). The ProACT project is investigating ways wearable, home sensors and tablet applications can be used to help persons with multimorbidity, as well as their support actors, which include informal caregivers (e.g. The project includes proof-of-concept trials in Ireland and Belgium, involving national health services, with a number of patients equipped with wearable and home sensors, and their support actors.

Pricing is a common problem faced by businesses, and one that can be addressed effectively by Bayesian statistical methods. We'll step through a simple example and build the background necessary to extend get involved with this approach. Let's start with some hypothetical data. A small company has tried a few different price points (say, one week each) and recorded the demand at each price. We'll abstract away some economic issues in order to focus on the statistical approach.

In the last two articles about Q-learning and Deep Q learning, we worked with value-based reinforcement learning algorithms. To choose which action to take given a state, we take the action with the highest Q-value (maximum expected future reward I will get at each state). As a consequence, in value-based learning, a policy exists only because of these action-value estimates. Today, we'll learn a policy-based reinforcement learning technique called Policy Gradients. The first will learn to keep the bar in balance.

Artificial intelligence owes a lot of its smarts to Judea Pearl. In the 1980s he led efforts that allowed machines to reason probabilistically. In his latest book, "The Book of Why: The New Science of Cause and Effect," he argues that artificial intelligence has been handicapped by an incomplete understanding of what intelligence really is. Three decades ago, a prime challenge in artificial intelligence research was to program machines to associate a potential cause to a set of observable conditions. Pearl figured out how to do that using a scheme called Bayesian networks.

The analysis of complex systems such as inventory control, financial markets, waste-to-energy plants and computer networks is difficult because of the inherent uncertainties in these systems. Risk-aware optimization offers a possible remedy by giving stronger reliability guarantees than the risk-neutral case. Furthermore, it allows expression of the risk attitude of the decision maker. Risk awareness is especially important in sequential decision making because of the dynamic nature of the uncertainty. Markov decision processes (MDPs) introduced by Bellman in [10] provide a mathematical framework for modeling sequential decision making in situations where outcomes are partly random and partly under the control the decision maker. However, in many cases the exact model of the underlying Markov decision process is not known and one can only observe the trajectory of states, actions, and rewards/costs.

We introduce the open-ended, modular, self-improving Omega AI unification architecture which is a refinement of Solomonoff's Alpha architecture, as considered from first principles. The architecture embodies several crucial principles of general intelligence including diversity of representations, diversity of data types, integrated memory, modularity, and higher-order cognition. We retain the basic design of a fundamental algorithmic substrate called an "AI kernel" for problem solving and basic cognitive functions like memory, and a larger, modular architecture that re-uses the kernel in many ways. Omega includes eight representation languages and six classes of neural networks, which are briefly introduced. The architecture is intended to initially address data science automation, hence it includes many problem solving methods for statistical tasks. We review the broad software architecture, higher-order cognition, self-improvement, modular neural architectures, intelligent agents, the process and memory hierarchy, hardware abstraction, peer-to-peer computing, and data abstraction facility.

Recent approaches for dialogue act recognition have shown that context from preceding utterances is important to classify the subsequent one. It was shown that the performance improves rapidly when the context is taken into account. We propose an utterance-level attention-based bidirectional recurrent neural network (Utt-Att-BiRNN) model to analyze the importance of preceding utterances to classify the current one. In our setup, the BiRNN is given the input set of current and preceding utterances. Our model outperforms previous models that use only preceding utterances as context on the used corpus. Another contribution of the article is to discover the amount of information in each utterance to classify the subsequent one and to show that context-based learning not only improves the performance but also achieves higher confidence in the classification. We use character- and word-level features to represent the utterances. The results are presented for character and word feature representations and as an ensemble model of both representations. We found that when classifying short utterances, the closest preceding utterances contributes to a higher degree.

Understanding and following directions provided by humans can enable robots to navigate effectively in unknown situations. We present FollowNet, an end-to-end differentiable neural architecture for learning multi-modal navigation policies. FollowNet maps natural language instructions as well as visual and depth inputs to locomotion primitives. FollowNet processes instructions using an attention mechanism conditioned on its visual and depth input to focus on the relevant parts of the command while performing the navigation task. Deep reinforcement learning (RL) a sparse reward learns simultaneously the state representation, the attention function, and control policies. We evaluate our agent on a dataset of complex natural language directions that guide the agent through a rich and realistic dataset of simulated homes. We show that the FollowNet agent learns to execute previously unseen instructions described with a similar vocabulary, and successfully navigates along paths not encountered during training. The agent shows 30% improvement over a baseline model without the attention mechanism, with 52% success rate at novel instructions.