Deep Learning goes right from the simplest data structures like lists to complicated ones like computation graphs.
Here are the most common ones:
- List: An ordered sequence of elements (You can also mention NumPy ndarrays here)
- Matrix: An ordered sequence of elements with rows and columns
- Dataframe: A dataframe is just like a matrix, but it holds actual data with the column names and rows denoting each datapoint in your dataset. If marks of 100 students, their grades, and their details are stored in a dataframe, their details are stored as columns. Each row will represent the data of each of the 100 students
- Tensors: You will work with them on a daily basis if you have ventured into deep learning. Used both in PyTorch and TensorFlow, tensors are like the basic programming unit of deep learning. Just like multidimensional arrays, we can perform numerous mathematical operations on them. Read more about tensors here
- Computation Graphs: Since deep learning involves multiple layers and often hundreds, if not thousands of parameters, it is important to understand the flow of computation. A computation graph is just that. A computation graph gives us the sequence of operations performed with each node denoting an operation or a component in the neural network