Posts

As we enter the digital age, one thing is certain: technology is not just a trend, it's a game-changer. With each passing day, technology is making its way into more and more industries, bringing about a variety of benefits for society such as increased efficiency, improved communication, and access to information. But, with change comes challenges, and one of the biggest concerns is the displacement of jobs. Neural tangent kernel (NTK) (Jacot et al. 2018) is a kernel to explain the evolution of neural networks during training via gradient descent....

Debugging deep learning models is a complex and challenging task that requires significant expertise and experience. One of the main reasons for this complexity is that deep learning models involve multiple layers of interconnected nodes, which can make it difficult to pinpoint the source of errors or identify areas where optimization is needed. Additionally, deep learning models often rely on large amounts of data to train, which can increase the risk of overfitting or underfitting the model. This is why it is essential to have a deep understanding of both the deep learning model itself, as well as the data from which the model is being trained, when it comes to debugging deep learning models.....

Are you tired of making predictions based on correlation rather than causation? Introducing Causality in Machine Learning, a cutting-edge approach to understanding the underlying causes of complex data patterns. By incorporating causal inference techniques, we can gain a deeper understanding of how different variables interact and affect each other, leading to more accurate predictions and informed decision-making....

Although most popular and successful model architectures are designed by human experts, it doesn’t mean we have explored the entire network architecture space and settled down with the best option. We would have a better chance to find the optimal solution if we adopt a systematic and automatic way of learning high-performance model architectures. Automatically learning and evolving network topologies is not a new idea (Stanley & Miikkulainen, 2002). In recent years, the pioneering work by Zoph & Le 2017 and Baker et al....