Filip Szatkowski
  • About Me
  • Work
  • Academic Career
  • Research
  • Papers
  • Events
  • Volunteering
  • 📄 CV
  • Recent & Upcoming Talks
    • Example Talk
  • Papers
    • Failure Prediction Is a Better Performance Proxy for Early-Exit Networks Than Calibration
    • Universal Properties of Activation Sparsity in Modern Large Language Models
    • ExpertSim: Fast Particle Detector Simulation Using Mixture-of-Generative-Experts
    • Improving Continual Learning Performance and Efficiency with Auxiliary Classifiers
    • Do LLMs Understand the Safety of Their Inputs? Training-Free Moderation via Latent Prototypes
    • Exploring the Stability Gap in Continual Learning: The Role of the Classification Head
    • Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion
    • Sparser, Better, Deeper, Stronger: Improving Static Sparse Training with Exact Orthogonal Initialization
    • Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-Free Continual Learning
    • Zero Time Waste in Pre-trained Early Exit Neural Networks
    • Hypernetworks Build Implicit Neural Representations of Sounds
    • Progressive Latent Replay for Efficient Generative Rehearsal
  • Blog
    • 🎉 Easily create your own simple yet highly customizable blog
    • 🧠 Sharpen your thinking with a second brain
    • 📈 Communicate your results effectively with the best data visualizations
    • 👩🏼‍🏫 Teach academic courses
    • ✅ Manage your projects
  • Projects
    • Pandas
    • PyTorch
    • scikit-learn
  • Teaching
    • Learn JavaScript
    • Learn Python

PyTorch

Oct 26, 2023 · 1 min read
Site

PyTorch is a Python package that provides tensor computation (like NumPy) with strong GPU acceleration.

Last updated on Oct 26, 2023
Hugo HugoBlox Markdown
Filip Szatkowski
Authors
Filip Szatkowski (he/him)
PhD Student
← Pandas Oct 26, 2023
scikit-learn Oct 26, 2023 →

© 2025 Me. This work is licensed under CC BY NC ND 4.0

Published with Hugo Blox Builder — the free, open source website builder that empowers creators.