Towards AI newsletter #102: GenAI advances beginning to benefit weather forecasting?
Author(s): Towards AI Editorial Team Originally published on Towards AI. Microsoftβs Aurora, Codestral, MoRA, XAi raise & more. What happened this week in AI by Louie While there was plenty of newsflow in the LLM world again this week, we are also …
Token-wise Influential Training Data Retrieval for Large Language Models
Author(s): Reza Yazdanfar Originally published on Towards AI. Iβm working on a powerful product, nouswise, go and check it out. Itβs in the beta phase, if it interests you hit me up on X. Itβs important to know which response corresponds to …
The Architecture of Mistralβs Sparse Mixture of Experts (Sγ½οΈβE)
Author(s): JAIGANESAN Originally published on Towards AI. Exploring Feed Forward Networks, Gating Mechanism, Mixture of Experts (MoE), and Sparse Mixture of Experts (SMoE). Photo by Ticka Kao on Unsplash Introduction:🥳 In this article, weβll dive deeper into the specifics of Mistralβs SMoE …
Using Neural Networks with Pytorch to Predict Fail of Automatic Recovery
Author(s): Greg Postalian-Yrausquin Originally published on Towards AI. This exercise is part of aproject implemented on a hardware system. The system has automatic doors that allow to be recovered when they fail to operate by the user (to cover the scenario of …
Unsupervised Clustering: Can We Identify Clusters in the Descriptions of Sounds in Music?
Author(s): Greg Postalian-Yrausquin Originally published on Towards AI. The data used is tricky because it is a list of Spotify songs, which are assigned values that describe the sounds in them. At this point, the goal is to see if those descriptions …
How To Use Target Encoding in Machine Learning Credit Risk Models β Part 1
Author(s): Varun Nakra Originally published on Towards AI. Target encoding, also known as mean encoding or likelihood encoding, is a technique used to convert categorical variables into numerical values based on the target variable in supervised learning tasks. This method is particularly …
Deep Exploratory Analysis and Random Forest Classification
Author(s): Greg Postalian-Yrausquin Originally published on Towards AI. Decision tree types of classification algorithms have the advantage that they produce results that are relatively easier to explain in terms of the impact of the predictors when compared to other supervised training algorithms, …
Use of Pretrained BERT to Predict the Rating of Reviews
Author(s): Greg Postalian-Yrausquin Originally published on Towards AI. BERT is a state-of-the-art algorithm designed by Google to process text data and convert it into vectors (https://en.wikipedia.org/wiki/BERT_(language_model) . These can then by analyzed by other models (classification, clustering, etc) to produce different analyses. …
Web scraping & NLP
Author(s): Greg Postalian-Yrausquin Originally published on Towards AI. In this example, I extract data from a Wikipedia list of the most grossing movies go into each of the links and fetch the text of the movieβs article. Then I use BERTopic (which …
Quick and Easy Application of Network Graph Analysis: Measure Connectivity Between Countries by Air Traffic
Author(s): Greg Postalian-Yrausquin Originally published on Towards AI. I use the Networkx package to analyze a set of air routes between a group of countries and describe how they are connected. Networkx is documented in the following publication: Aric A. Hagberg, Daniel …
Descriptive Analysis
Author(s): Greg Postalian-Yrausquin Originally published on Towards AI. Descriptive analytics is a big part of working with data, it could be before more complicated tasks, such as machine learning or on its own. In this example I illustrate the use of deep …
Low-Rank Adaptation (LoRA): From Intuition to Implementation to Interview Questions
Author(s): Harsh Maheshwari Originally published on Towards AI. Delving Deeper into LoRA for LLMsPhoto by Digital Content Writers India on Unsplash LLM are getting larger and larger each day, recently, Meta has announced that they are currently working on the 400b Llama …
Using NLP (Doc2Vec) and Neural Networks (with Keras): Removing Hate Speech and Offensive Tweets
Author(s): Greg Postalian-Yrausquin Originally published on Towards AI. This is a great example of how more than one ML step can be used to achieve a goal. In this exercise, I will combine NLP (Doc2Vec) with binary classification to extract offensive and …
Synthetic Data Generation in Foundation Models and Differential Privacy: Three Papers from Microsoft Research
Author(s): Jesus Rodriguez Originally published on Towards AI. Created Using Ideogram I recently started an AI-focused educational newsletter, that already has over 170,000 subscribers. TheSequence is a no-BS (meaning no hype, no news, etc) ML-oriented newsletter that takes 5 minutes to read. …
Satellite Image Classification with Machine Learning & Python β Part 1: Creating Model and Classifying
Author(s): KokaTic Originally published on Towards AI. Study region of our tutorial β El Oued, Algeria (source: Bing maps) Image classification is a pivotal task in the realm of machine learning, particularly within the domain of remote sensing. In this series, we …