Highlights: Welcome back to the all-new series on Machine Learning. In the previous post, we gave you a sneak peak into the basics of Machine Learning, the two types of Machine Learning, viz., Supervised & Unsupervised, and implemented some examples using various algorithms in each of the techniques. In this new tutorial post, we will explore one of the most widely used Supervised Learning algorithms in the world today – Linear Regression. We will start off with some theory and go on to build a simple model in Python, from scratch. In our previous post (also the first post of this Machine Learning tutorial series), we brushed the fundamentals of Linear Regression using the example of housing price prediction, given the size of the house. If you remember, the prediction was based on the linear relationship that existed between the house price and the size of the house. Have a look at the image below. In the graph above, the size of the house is shown along the horizontal axis and the price of a house is shown along the vertical axis. Here, each data point is a house with its respective size and the price that the house was recently sold for.

Machine learning (ML) is everywhere these days. It helps us better detect malware and insider threats by continuously analyzing data to find patterns. It increases our productivity, improves service quality, and can even entertain us by recommending the movies we are likely to enjoy. ML capabilities have pushed a lot of people to start exploring machine learning, but writing algorithms and programs for ML isn't easy and requires significant mathematical knowledge. This track will build the basic foundation required for ML model development. It breaks down complicated mathematical concepts into easy-to-read theory followed by practical tasks.

Below gives you a sense of how we're thinking about what you'll need to be successful in the role.

Our daily lives are being impacted by artificial intelligence (AI) in several ways. Artificial assistants, predictive models, and facial recognition systems are practically ubiquitous. Numerous sectors use AI, including education, healthcare, automobiles, manufacturing, and law enforcement. The judgments and forecasts provided by AI-enabled systems are becoming increasingly more significant and, in many instances, vital to survival. This is particularly true for AI systems used in healthcare, autonomous vehicles, and even military drones.

The universe is noisy and confusing, complex enough to make predictions difficult. Human intelligence and intuition facilitate a basic understanding of some of the activities of the world around us. And they do so well enough to make basic sense of events at the macro space and time scales of the limited perspectives of individuals and small groups. The natural philosophers of human prehistory and early history were mostly limited to common sense rationalization and guess and check. The limitations of these methods, especially for things that are just too big or too complex, are readily apparent in the prevalence and influence of superstition and magical thinking.

Energy has been propelling the development of human civilization for millennia, and technologies acquiring energy beyond human and animal power have been continuously advanced and transformed. In 1964, the Kardashev Scale was proposed to quantify the relationship between energy consumption and the development of civilizations. Human civilization presently stands at Type 0.7276 on this scale. Projecting the future energy consumption, estimating the change of its constituting structure, and evaluating the influence of possible technological revolutions are critical in the context of civilization development. In this study, we use two machine learning models, random forest (RF) and autoregressive integrated moving average (ARIMA), to simulate and predict energy consumption on a global scale. We further project the position of human civilization on the Kardashev Scale in 2060. The result shows that the global energy consumption is expected to reach 928-940 EJ in 2060, with a total growth of over 50% in the coming 40 years, and our civilization is expected to achieve Type 0.7474 on the Kardashev Scale, still far away from a Type 1 civilization. Additionally, we discuss the potential energy segmentation change before 2060 and present the influence of the advent of nuclear fusion in this context.

Finding optimal message quantization is a key requirement for low complexity belief propagation (BP) decoding. To this end, we propose a floating-point surrogate model that imitates quantization effects as additions of uniform noise, whose amplitudes are trainable variables. We verify that the surrogate model closely matches the behavior of a fixed-point implementation and propose a hand-crafted loss function to realize a trade-off between complexity and error-rate performance. A deep learning-based method is then applied to optimize the message bitwidths. Moreover, we show that parameter sharing can both ensure implementation-friendly solutions and results in faster training convergence than independent parameters. We provide simulation results for 5G low-density parity-check (LDPC) codes and report an error-rate performance within 0.2 dB of floating-point decoding at an average message quantization bitwidth of 3.1 bits. In addition, we show that the learned bitwidths also generalize to other code rates and channels.

A sememe is defined as the minimum semantic unit of human languages. Sememe knowledge bases (KBs), which contain words annotated with sememes, have been successfully applied to many NLP tasks, and we believe that by learning the smallest unit of meaning, computers can more easily understand human language. However, Existing sememe KBs are built on only manual annotation, human annotations have personal understanding biases, and the meaning of vocabulary will be constantly updated and changed with the times, and artificial methods are not always practical. To address the issue, we propose an unsupervised method based on a deep clustering network (DCN) to build a sememe KB, and you can use any language to build a KB through this method. We first learn the distributed representation of multilingual words, use MUSE to align them in a single vector space, learn the multi-layer meaning of each word through the self-attention mechanism, and use a DNC to cluster sememe features. Finally, we completed the prediction using only the 10-dimensional sememe space in English. We found that the low-dimensional space can still retain the main feature of the sememes.

In recent studies, self-supervised pre-trained models tend to outperform supervised pre-trained models in transfer learning. In particular, self-supervised learning (SSL) of utterance-level speech representation can be used in speech applications that require discriminative representation of consistent attributes within an utterance: speaker, language, emotion, and age. Existing frame-level self-supervised speech representation, e.g., wav2vec, can be used as utterance-level representation with pooling, but the models are usually large. There are also SSL techniques to learn utterance-level representation. One of the most successful is a contrastive method, which requires negative sampling: selecting alternative samples to contrast with the current sample (anchor). However, this does not ensure that all the negative samples belong to classes different from the anchor class without labels. This paper applies a non-contrastive self-supervised method to learn utterance-level embeddings. We adapted DIstillation with NO labels (DINO) from computer vision to speech. Unlike contrastive methods, DINO does not require negative sampling. We compared DINO to x-vector trained in a supervised manner. When transferred to down-stream tasks (speaker verification, speech emotion recognition (SER), and Alzheimer's disease detection), DINO outperformed x-vector. We studied the influence of several aspects during transfer learning such as dividing the fine-tuning process into steps, chunk lengths, or augmentation. During fine-tuning, tuning the last affine layers first and then the whole network surpassed fine-tuning all at once. Using shorter chunk lengths, although they generate more diverse inputs, did not necessarily improve performance, implying speech segments at least with a specific length are required for better performance per application. Augmentation was helpful in SER.

We propose a novel model selection algorithm based on a penalized maximum likelihood estimator (PMLE) for functional hidden dynamic geostatistical models (f-HDGM). These models employ a classic mixed-effect regression structure with embedded spatiotemporal dynamics to model georeferenced data observed in a functional domain. Thus, the parameters of interest are functions across this domain. The algorithm simultaneously selects the relevant spline basis functions and regressors that are used to model the fixed-effects relationship between the response variable and the covariates. In this way, it automatically shrinks to zero irrelevant parts of the functional coefficients or the entire effect of irrelevant regressors. The algorithm is based on iterative optimisation and uses an adaptive least absolute shrinkage and selector operator (LASSO) penalty function, wherein the weights are obtained by the unpenalised f-HDGM maximum-likelihood estimators. The computational burden of maximisation is drastically reduced by a local quadratic approximation of the likelihood. Through a Monte Carlo simulation study, we analysed the performance of the algorithm under different scenarios, including strong correlations among the regressors. We showed that the penalised estimator outperformed the unpenalised estimator in all the cases we considered. We applied the algorithm to a real case study in which the recording of the hourly nitrogen dioxide concentrations in the Lombardy region in Italy was modelled as a functional process with several weather and land cover covariates.