Interview Preparation
ML Fundamentals
Core concepts behind generalization, regularization, normalization, and dropout
Interview Preparation
Optimization & Training
Backpropagation, optimizers, activations, and initialization
Interview Preparation
Classification & Information Theory
SVM, logits and softmax, entropy, cross-entropy, and KL divergence
Interview Preparation
Linear Algebra & Decomposition
Vector-space basics, norms, eigen/SVD decompositions, LoRA, and PCA
Interview Preparation
Probability & Bayesian Inference
Bayes' theorem, MLE/MAP, and the canonical distributions used in ML
Interview Preparation
Optimization Theory
Convexity, Lipschitz smoothness, and constrained optimization via Lagrangian duality
Interview Preparation
Regression
Linear and logistic regression with a probabilistic interpretation
Interview Preparation
CNN & ResNet
Convolutional layers, parameter-efficient variants, and residual learning for deep networks
Interview Preparation
Sequence Models
From RNNs to Transformers and ViT, with attention mechanisms, positional encodings, and complexity
Interview Preparation
AutoEncoder · VAE · GAN
AutoEncoders, VAEs, GANs, and generative model evaluation metrics
Interview Preparation
Diffusion · Flow Matching · SDE Score
Denoising diffusion, classifier-free guidance, flow matching, SDE-based score models, and DiT
Interview Preparation
Conditioning & Distillation
Knowledge distillation and conditioning adapters for pretrained diffusion models
Interview Preparation
3D Neural Rendering
NeRF, neural tangent kernels, InstantNGP, and 3D Gaussian Splatting for novel-view synthesis