The search for biologically faithful synaptic plasticity rules has resulted in a large body of models. They are usually inspired by -- and fitted to -- experimental data, but they rarely produce neural dynamics that serve complex functions. These failures suggest that current plasticity models are still under-constrained by existing data. Here, we present an alternative approach that uses meta-learning to discover plausible synaptic plasticity rules. Instead of experimental data, the rules are constrained by the functions they implement and the structure they are meant to produce.

Enhancing large language models (LLMs) with real-time APIs can help generate more accurate and up-to-date responses. However, evaluating the function calling abilities of LLMs in real-world scenarios remains under-explored due to the complexity of data collection and evaluation. In this work, we introduce ComplexFuncBench, a benchmark for complex function calling across five real-world scenarios. Compared to existing benchmarks, ComplexFuncBench encompasses multi-step and constrained function calling, which requires long-parameter filing, parameter value reasoning, and 128k long context. Additionally, we propose an automatic framework, ComplexEval, for quantitatively evaluating complex function calling tasks. Through comprehensive experiments, we demonstrate the deficiencies of state-of-the-art LLMs in function calling and suggest future directions for optimizing these capabilities. The data and code are available at \url{https://github.com/THUDM/ComplexFuncBench}.

The search for biologically faithful synaptic plasticity rules has resulted in a large body of models. They are usually inspired by -- and fitted to -- experimental data, but they rarely produce neural dynamics that serve complex functions. These failures suggest that current plasticity models are still under-constrained by existing data. Here, we present an alternative approach that uses meta-learning to discover plausible synaptic plasticity rules. Instead of experimental data, the rules are constrained by the functions they implement and the structure they are meant to produce.

The aviation literature gives relatively little guidance to practitioners about the specifics of architecting systems for safety, particularly the impact of architecture on allocating safety requirements, or the relative ease of system assurance resulting from system or subsystem level architectural choices. As an exemplar, this paper considers common architectural patterns used within traditional aviation systems and explores their safety and safety assurance implications when applied in the context of integrating artificial intelligence (AI) and machine learning (ML) based functionality. Considering safety as an architectural property, we discuss both the allocation of safety requirements and the architectural trade-offs involved early in the design lifecycle. This approach could be extended to other assured properties, similar to safety, such as security. We conclude with a discussion of the safety considerations that emerge in the context of candidate architectural patterns that have been proposed in the recent literature for enabling autonomy capabilities by integrating AI and ML. A recommendation is made for the generation of a property-driven architectural pattern catalogue.

In case your high school math is rusty, these are arbitrary functions we made up that, when graphed, produce various lines and curves. The abstract notion of a mathematical function turns out to be so powerful precisely because it lets us use our understanding of simple instances to reason about relatives of arbitrary complexity. By this definition, all the AI systems in use today, including the LaMDA chatbot that triggered the recent controversy, are functions. Placing LaMDA alongside its fellow functions takes the wind out of the sails of those who, dazed and confused by complexity, reach for the familiar territory of moral judgments. Should our teachers have scolded us if we plotted a sentient function on a handheld calculator because of the suffering we might accidentally inflict upon this innocent lifeform?

The story of a Google engineer (and Christian mystic) who saw signs of personhood in Google's latest artificially intelligent chatbot software and was later fired has reignited public debate over whether any of today's AI systems are sentient. The consensus among experts is that no, they are not: see this, this, this, and this, for example. We reached the same conclusion via a different path, using a little mathematical formalism to burn off the fog of confusion. A chatbot is a function. But functions can be powerful.

We are excited to bring Transform 2022 back in-person July 19 and virtually July 20 - August 3. Join AI and data leaders for insightful talks and exciting networking opportunities. The use of deep learning has grown rapidly over the past decade, thanks to the adoption of cloud-based technology and use of deep learning systems in big data, according to Emergen Research, which expects deep learning to become a $93 billion market by 2028. But what exactly is deep learning and how does it work? Deep learning is a subset of machine learning which uses neural networks to perform learning and predictions. Deep learning has shown amazing performance in various tasks, whether it be text, time series or computer vision.

Machine learning (ML) is to train a machine so that it can make decisions for us. This can be achieved by expert system or machine learning. Expert system is a computer system that emulates the decision-making ability of a human expert. Expert system are also known as Rule Based Systems. It emulates how a human makes a decision.

Master functions and discover how to write functional programs in R. In this concise book, you'll make your functions pure by avoiding side-effects; you'll write functions that manipulate other functions, and you'll construct complex functions using simpler functions as building blocks. In Functional Programming in R, you'll see how we can replace loops, which can have side-effects, with recursive functions that can more easily avoid them. In addition, the book covers why you shouldn't use recursion when loops are more efficient and how you can get the best of both worlds. Functional programming is a style of programming, like object-oriented programming, but one that focuses on data transformations and calculations rather than objects and state. Where in object-oriented programming you model your programs by describing which states an object can be in and how methods will reveal or modify that state, in functional programming you model programs by describing how functions translate input data to output data.

What is going on in our brains when we are creating? How does our brain look different when we are engaging in art versus science? How does the brain of genius creators differ from the rest of us? What are some of the limitations of studying the creative brain? The neuroscience of creativity is booming.