Convolutional Neural Networks in PyTorch: Image Classification
Author(s): Greg Postalian-Yrausquin Originally published on Towards AI. In this exercise I will use the PyTorch package to build a convolutional neural network with the intention of training a model to classify a given set of images. Convolutional Neural Networks are different …
Mastering Evaluations in LangSmith: Enhancing LLM Performance
Author(s): Mostafa Ibrahim Originally published on Towards AI. Source Large Language Models (LLMs) are AI models capable of generating text that resembles human language. They are trained on extensive text datasets and are suitable for various natural language processing tasks, including translation, …
Classifying NBA Positions by Physical Traits β Part I
Author(s): Vishnu Regimon Nair Originally published on Towards AI. Photo by Markus Spiske on Unsplash In 2019, NBA teams spent over 3 billion dollars on guaranteed salaries to players in the first three days of free agency. These expensive contracts often lock …
The Rise of Vector Databases: Understanding Vector Search and RAG Pipeline
Author(s): Shwetha Acharya Originally published on Towards AI. What is a Vector? Vector is an object that possesses both magnitude and direction. It is represented as an array of numbers that define its dimensionality. Here is an example of how vectors β …
Evaluating LLM Applications Using LangChain
Author(s): Youssef Hosni Originally published on Towards AI. Hands-On LangChain for LLM Application Development When constructing a sophisticated application employing an LLM, a crucial yet challenging aspect revolves around evaluating its performance. How can you ascertain if it meets accuracy standards? Moreover, …
Technical Post-Mortem of a Data Migration Event
Author(s): Vishnu Regimon Nair Originally published on Towards AI. Key Objectives of Data Migration. Image by Author In this data-driven landscape, extracting the maximum value from data is crucial for success. As data volumes grow exponentially, organizations face considerable pressure to optimize …
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 …
Popular posts
Updates
Recent Posts
