While current time series research focuses on developing new models, crucial questions of selecting an optimal approach for training such models are underexplored. Tsururu, a Python library introduced in this paper, bridges SoT A research and industry by enabling flexible combinations of global and multivariate approaches and multi-step-ahead forecasting strategies. It also enables seamless integration with various forecasting models.

Modern NLP tasks increasingly rely on dense retrieval methods to access up-to-date and relevant contextual information. We are motivated by the premise that retrieval benefits from segments that can vary in size such that a content's semantic independence is better captured. We propose LumberChunker, a method leveraging an LLM to dynamically segment documents, which iteratively prompts the LLM to identify the point within a group of sequential passages where the content begins to shift. To evaluate our method, we introduce GutenQA, a benchmark with 3000 "needle in a haystack" type of question-answer pairs derived from 100 public domain narrative books available on Project Gutenberg. Our experiments show that LumberChunker not only outperforms the most competitive baseline by 7.37% in retrieval performance (DCG@20) but also that, when integrated into a RAG pipeline, LumberChunker proves to be more effective than other chunking methods and competitive baselines, such as the Gemini 1.5M Pro. Our Code and Data are available at https://github.com/joaodsmarques/LumberChunker

I will describe my recent results on the automatic development of fixed(cid:173) width recursive distributed representations of variable-sized hierarchal data structures. One implication of this wolk is that certain types of AI-style data-structures can now be represented in fixed-width analog vectors. Simple inferences can be perfonned using the type of pattern associations that neural networks excel at Another implication arises from noting that these representations become self-similar in the limit Once this door to chaos is opened.

Sustainable development goals (SDGs) are becoming more and more important for companies of all shapes and sizes. Put simply, SDGs are a collection of 17 interlinked goals designed to help companies achieve a more sustainable future. Set in 2015 by the UN General Assembly, these goals aim to support such efforts as making processes more efficient, reducing waste, creating diversity, and improving education. Artificial intelligence is one way that these sustainable development goals can be achieved, but leveraging the technology is no simple task. To learn more about the use of machine learning and AI technology for SDGs, we talked to Tiago Ramalho, the founder of Recursive.

Markov decision processes (MDPs) and partially observable MDPs (POMDPs) can effectively represent complex real-world decision and control problems. However, continuous space MDPs and POMDPs, i.e. those having continuous state, action and observation spaces, are extremely difficult to solve, and there are few online algorithms with convergence guarantees. This paper introduces Voronoi Progressive Widening (VPW), a general technique to modify tree search algorithms to effectively handle continuous or hybrid action spaces, and proposes and evaluates three continuous space solvers: VOSS, VOWSS, and VOMCPOW. VOSS and VOWSS are theoretical tools based on sparse sampling and Voronoi optimistic optimization designed to justify VPW-based online solvers. While previous algorithms have enjoyed convergence guarantees for problems with continuous state and observation spaces, VOWSS is the first with global convergence guarantees for problems that additionally have continuous action spaces. VOMCPOW is a versatile and efficient VPW-based algorithm that consistently outperforms POMCPOW and BOMCP in several simulation experiments.

Parameter-free stochastic gradient descent (PFSGD) algorithms do not require setting learning rates while achieving optimal theoretical performance. In practical applications, however, there remains an empirical gap between tuned stochastic gradient descent (SGD) and PFSGD. In this paper, we close the empirical gap with a new parameter-free algorithm based on continuous-time Coin-Betting on truncated models. The new update is derived through the solution of an Ordinary Differential Equation (ODE) and solved in a closed form. We show empirically that this new parameter-free algorithm outperforms algorithms with the "best default" learning rates and almost matches the performance of finely tuned baselines without anything to tune.

Sometimes we just need clearly outlined steps instructing on how to implement a machine learning or data science project. This article aims to provide an end-to-end guide for implementing a successful machine learning project. It can be over-whelming to write the entire guide as one article. Keeping that in mind, I have written a number of easy-to-understand articles and provided their links here so that the readers can understand the steps and navigate to the appropriate article if required. We find many informative articles online that provide an in-depth coverage of how we need to implement parts of a machine learning/data science project but at times, we just need high level steps offering clear guidance.

For the past few days I've been working on how to implement recursive neural networks in TensorFlow. Recursive neural networks (which I'll call TreeNets from now on to avoid confusion with recurrent neural nets) can be used for learning tree-like structures (more generally, directed acyclic graph structures). They are highly useful for parsing natural scenes and language; see the work of Richard Socher (2011) for examples. More recently, in 2014, Ozan İrsoy used a deep variant of TreeNets to obtain some interesting NLP results. In RNNs, at each time step the network takes as input its previous state s(t-1) and its current input x(t) and produces an output y(t) and a new hidden state s(t).

In RNNs, at each time step the network takes as input its previous state s(t-1) and its current input x(t) and produces an output y(t) and a new hidden state s(t). TreeNets, on the other hand, don't have a simple linear structure like that. With RNNs, you can'unroll' the net and think of it as a large feedforward net with inputs x(0), x(1), …, x(T), initial state s(0), and outputs y(0),y(1),…,y(T), with T varying depending on the input data stream, and the weights in each of the cells tied with each other. You can also think of TreeNets by unrolling them – the weights in each branch node are tied with each other, and the weights in each leaf node are tied with each other. The TreeNet illustrated above has different numbers of inputs in the branch nodes.

For the past few days I've been working on how to implement recursive neural networks in TensorFlow. Recursive neural networks (which I'll call TreeNets from now on to avoid confusion with recurrent neural nets) can be used for learning tree-like structures (more generally, directed acyclic graph structures). They are highly useful for parsing natural scenes and language; see the work of Richard Socher (2011) for examples. More recently, in 2014, Ozan İrsoy used a deep variant of TreeNets to obtain some interesting NLP results. In RNNs, at each time step the network takes as input its previous state s(t-1) and its current input x(t) and produces an output y(t) and a new hidden state s(t).