Symbolic regression (SR) is a challenging task in machine learning that involves finding a mathematical expression for a function based on its values. Recent advancements in SR have demonstrated the effectiveness of pre-trained transformer models in generating equations as sequences, leveraging large-scale pre-training on synthetic datasets and offering notable advantages in terms of inference time over classical Genetic Programming (GP) methods. However, these models primarily rely on supervised pre-training objectives borrowed from text generation and overlook equation discovery goals like accuracy and complexity. To address this, we propose TPSR, a Transformer-based Planning strategy for Symbolic Regression that incorporates Monte Carlo Tree Search planning algorithm into the transformer decoding process. Unlike conventional decoding strategies, TPSR enables the integration of non-differentiable equation verification feedback, such as fitting accuracy and complexity, as external sources of knowledge into the transformer equation generation process. Extensive experiments on various datasets show that our approach outperforms state-of-the-art methods, enhancing the model's fitting-complexity trade-off, extrapolation abilities, and robustness to noise.

Symbolic regression (SR) is a challenging task in machine learning that involves finding a mathematical expression for a function based on its values. Recent advancements in SR have demonstrated the effectiveness of pre-trained transformer models in generating equations as sequences, leveraging large-scale pre-training on synthetic datasets and offering notable advantages in terms of inference time over classical Genetic Programming (GP) methods. However, these models primarily rely on supervised pre-training objectives borrowed from text generation and overlook equation discovery goals like accuracy and complexity. To address this, we propose TPSR, a Transformer-based Planning strategy for Symbolic Regression that incorporates Monte Carlo Tree Search planning algorithm into the transformer decoding process. Unlike conventional decoding strategies, TPSR enables the integration of non-differentiable equation verification feedback, such as fitting accuracy and complexity, as external sources of knowledge into the transformer equation generation process.

The authors propose a mathematical programming approach to build interpretable machine learning models. In this case, the interpretable model is a system of Boolean rules in disjunctive (or conjunctive) normal form which is constructed using column generation for the linear relaxation of a mixed integer program (MIP) designed to minimize the number of positive samples classified incorrectly and the complexity of the learned system subject to complexity constraints. To remedy the fact that there are exponentially many potential clauses to optimize over, the authors propose a standard column generation approach that prices potential columns to add and solves a secondary integer program to find such potential columns. The authors also note that the column generation can also be done via heuristics or a greedy algorithm. Once the linear programming program is solved or reaches its time limit, the approach then solves the global mixed integer formulation to get a final set of rules.

Hand gestures constitute another important mode of human communication that could be adopted for human-computer interactions. Recent progress in camera systems, image analysis, and machine learning have made optical-based gesture recognition a more attractive option in most contexts than approaches relying on wearable sensors or data gloves, as used by Anderton in Minority Report. However, current methods are hindered by a variety of limitations, including high computational complexity, low speed, poor accuracy, or a low number of recognizable gestures. To tackle these issues, a team led by Zhiyi Yu of Sun Yat-sen University, China, recently developed a new hand gesture recognition algorithm that strikes a good balance between complexity, accuracy, and applicability. As detailed in their paper, which was published in the Journal of Electronic Imaging, the team adopted innovative strategies to overcome key challenges and realize an algorithm that can be easily applied in consumer-level devices.

Although deep neural networks (NNs) have achieved state-of-the-art accuracy in many visual recognition tasks ,the growing computational complexity and energy consumption of networks remains an issue, especially for applications on platforms with limited resources and requiring real-time processing. Channel pruning techniques have recently shown promising results for the compression of convolutional NNs (CNNs). However, these techniques can result in low accuracy and complex optimisations because some only prune after training CNNs, while others prune from scratch during training by integrating sparsity constraints or modifying the loss function. The progressive soft filter pruning technique provides greater training efficiency, but its soft pruning strategy does no thandle the backward pass which is needed for better optimization. In this paper, a new Progressive Gradient Pruning (PGP) technique is proposed for iterative channel pruning during training. It relies on a criterion that measures the change in channel weights that improves existing progressive pruning, and on an effective hard and soft pruning strategies to adapt momentum tensors during the backward propagation pass. Experimental results obtained after training various CNNs on the MNIST and CIFAR10 datasets indicate that the PGP technique canachieve a better tradeoff between classification accuracy and network (time and memory) complexity than state-of-the-art channel pruning techniques