Repository for the Neural Networks laboratory, "Alexandru Ioan Cuza" University, Faculty of Computer Science, Bachelor degree.
Google Colab: PyTorch, Pandas, and Numpy are already available.
Local instalation:
- Create a Python environment (using conda or venv). We recommend installing conda from Miniforge.
# Create the environment
conda create -n 312 -c conda-forge python=3.12
# activate the environment
conda activate 312
# Run this to use conda-forge as your highest priority channel (not needed if you installed conda from Miniforge)
conda config --add channels conda-forge
- Install PyTorch 2.4.1+ from pytorch.org using
condaorpip, depending on your environment.- Choose the Stable Release, choose your OS, select Conda or Pip and your compute platform. For Linux and Windows, CUDA or CPU builds are available, while for Mac, only builds with CPU and MPS acceleration.
- Example CPU:
conda install pytorch torchvision torchaudio cpuonly -c pytorch.
- Linear algebra:
- Essence of linear algebra (linear transformations; matrix multiplication)
- Essence of calculus (derivatives; chain rule)
- Backpropagation:
- Neural Networks (chapter 1 - chapter 4) (animated introduction to neural networks and backpropagation)
- If you want to learn more in advance, check our other recommended resources.
- Do check the Nice Links!
- Lab01 (Homework 1: Solve linear system)
- Lab02 (Homework 2: Perceptron implementation)
- Lab03 (Homework 3: Multilayer Perceptron implementation)
- Lab04
- Lab06 PyTorch Tensors, Autograd
- Lab09 Datasets, DataLoaders (Homework 4: PyTorch Pipeline)
- Lab10 Convolutions (Homework 5: Reinforcement Learning agent implementation)