About Myself
I’m Noah Schliesman, a recent EE graduate from the University of San Diego with minors in Computer Science and Math. I currently work as a Data Scientist for Data Annotation, where I perform audits of major LLM responses for complex math, computer science, and other STEM fields. From 2023-2024, I worked with Dr. Kathleen Kramer, CEO of IEEE, and Dr. Stephen Stubberud, Project Manager at General Atomics, to use neural networks in Kalman filtering to measure uncertainty and denoise signals. Before that, I served as a teaching assistant for courses in PDEs, linear algebra, and complex analysis. I’ve had the pleasure of working as an engineering intern with several engineering firms, including Infinitum Electric and Forensic Rock. I’m a lifelong learner, so please check out my analysis below!
Original Work and Primers
Sinusoidal Weights for Fourier Expressibility Hilbert Spaces Binary Classification in Supervised Learning RNNs, GRUs, and LSTMs Attention and Transformer Architectures DeepSeek-R1Annotated Papers
Perceptron Kalman Filter Backpropagation Backpropagation via Lagrangians Optimal Brain Damage Bidirectional RNNs Vanishing Gradient Support Vector Networks Greedy Layerwise Training Autoencoders Curriculum Learning ImageNet Classification with CNNs Word2Vec Seq2Seq Translation via Additive Attention Neural GPU Transformers m-gramsOriginal Animations
Single Neuron Activation