Freaks City

Data Preparation The dataset originates from a Kaggle competition involving store item demand forecasting. It contains 5 years of sales data (2013-2017) for 50 items across 10 stores, requiring predictions for the next 3 months (January-March 2018). This represents a multi-step multivariate time series problem with 500 distinct time series to f ...

PyTorch with CUDA 11.8 To install PyTorch 2.2.0 with CUDA 11.8 support: pip install torch==2.2.0+cu118 --extra-index-url https://download.pytorch.org/whl/cu118 PyTorch with CUDA 12.4 For CUDA 12.4 compatibility, use: pip install torch==2.4.0+cu124 --extra-index-url https://download.pytorch.org/whl/cu124 LMdeploy Minimum Requirements LMdeploy ...

The Fundamental Concept of Generalization Generalization represents one of the most critical concepts in machine learning. It describes how well a model trained on specific datasets performs when encountering previously unseen data. In machine learning workflows, we utilize training datasets to develop models that establish mapping relationship ...

Attention Mechanisms and Transformers The attention mechanism addresses a fundamental challenge in deep learning: transforming variable-dimensional inputs into fixed-dimensional outputs through a weighted aggregation process. This capability proves essential when dealing with sequences or sets of varying sizes, where traditional fixed-parameter ...

Nearest Neighbor and k-NN Classifiers The Nearest Neighbor classifier stores the entire training set and predicts labels by finding the closest training example using a distance metric like L1 (Manhattan) or L2 (Euclidean). While simple, it suffers from high prediction latency (O(n)) and large memory usage. class KNearestNeighbor: def init(sel ...

Task Overview Sentiment classification is a fundamantal task in Natural Language Processing (NLP) that involves categorizing text (such as reviews or tweets) based on emotional sentiment (e.g., binary classification: positive/negative). In this tutorial, we'll use the IMDB movie review dataset to implement three different models using PyTorch. ...

Automatic differentiation (AD) is a fundamental technique in deep learning frameworks. This article demonstrates how to implement forward-mode automatic differentiation using Python operator overloading. The implemantation is remarkably concise—you can build a working system in just a few lines of code. Understanding Forward-Mode Automatic Diff ...

Automatic differentiation (AD) computes exact derivatives efficiently by applying the chain rule during program execution. Two primary strategies exist: forward mode and reverse mode. Their suitability depends on the shape of the function being differentiated—specifically, the number of inputs versus outputs. Intuitive Analogy: Manufacturing Wo ...

Deep learning, a subset of machine learning, relies on neural networks with multiple layers to model complex patterns in data. At its core is the artificial neural network (ANN), inspired by biological neurons, which processes inputs through layered computations to produce meaningful outputs. Structure of a Neural Network A typical feedforward ...

TensorFlow 2.0 introduces significant improvements over previous versions, offering a simpler API surface, better usability, and enhanced performance. This article covers the major architectural shifts developers need to understand. Data Input with tf.data The tf.data API provides a unified mechanism for building efficient input pipelines. It h ...