Skip to main content
grasp.study
Back to course
Log in
Get started
Someone wanted to learn this too, so Grasp built them a personal learning path.
Create your own
Systems Engineering and Quant Internships
·
Module 1
Parallel, Time-Critical Track: Wunder Fund Connectome RNN Sprint
1
Vanishing and Exploding Gradients in Vanilla RNNs
Derive the hidden-state recurrence of a vanilla RNN and explain why long sequences can produce vanishing or exploding gradients.
2
Streaming Parquet Row Groups into PyTorch Efficiently
Stream sequence-sized row groups from Parquet into PyTorch without loading the full competition dataset into memory.
3
Reproducing Masked Global Weighted Pearson with Leakage-Safe Validation
Reproduce the competition's masked Global Weighted Pearson metric with a leakage-safe validation procedure.
4
Stateful GRU with Hidden-State Reset and Dual-Step Predictions
Implement a stateful GRU that resets hidden state between sequences and emits two predictions at each required step.
5
Training GRUs on Long Streams with Truncated BPTT and Gradient Clipping
Train the GRU on long streams using truncated backpropagation through time and gradient clipping.
6
Diagnosing Sequence-Model Overfitting Across Time and Instruments
Diagnose sequence-model overfitting by comparing training and validation behavior across time periods and instruments.
7
Exporting and Verifying Stateful PyTorch Sequence Models with ONNX Runtime
Export a stateful PyTorch sequence model to ONNX and verify numerical agreement with ONNX Runtime.
8
Benchmark and Validate Resource-Constrained Submissions
Profile, package, and validate a deterministic submission against the competition's one-CPU, 16-GB, 60-minute, and 20-MB limits.
Next module isn't ready yet,
Back to course
Previous module
Next module