This repo contains a list of topics which we feel that one should be comfortable with before appearing for a DL interview. This list is by no means exhaustive (as the field is very wide and ever growing).
- Linear Algebra(notes)
- Linear Dependence and Span
- Eigendecomposition
- Eigenvalues and Eigenvectors
- Singular Value Decomposition
- Probability and Statistics
- Expectation, Variance and Co-variance
- Distributions
- Bias and Variance
- Bias Variance Trade-off
- Estimators
- Biased and Unbiased
- Maximum Likelihood Estimation
- Maximum A Posteriori (MAP) Estimation
- Information Theory
- (Shannon) Entropy
- Cross Entropy
- KL Divergence
- Not a distance metric
- Derivation from likelihood ratio (Blog)
- Always greater than 0
- Proof by Jensen's Inequality
- Relation with Entropy (Explanation)
- Backpropogation
- Vanilla (blog)
- Backprop in CNNs
- Gradients in Convolution and Deconvolution Layers
- Backprop through time
- Loss Functions
- MSE Loss
- Derivation by MLE and MAP
- Cross Entropy Loss
- Binary Cross Entropy
- Categorical Cross Entropy
- MSE Loss
- Activation Functions (Sigmoid, Tanh, ReLU and variants) (blog)
- Optimizers
- Regularization
- Early Stopping
- Noise Injection
- Dataset Augmentation
- Ensembling
- Parameter Norm Penalties
- L1 (sparsity)
- L2 (smaller parameter values)
- BatchNorm (Paper)
- Internal Covariate Shift
- BatchNorm in CNNs (Link)
- Backprop through BatchNorm Layer (Explanation)
- Dropout (Paper) (Notes)
- ILSVRC
- Object Recognition (Blog)
- Convolution
- Cross-correlation
- Pooling (Average, Max Pool)
- Strides and Padding
- Output volume dimension calculation
- Deconvolution (Transpose Conv.), Upsampling, Reverse Pooling (Visualization)
- Recurrent Neural Networks
- Word Embeddings
- Word2Vec
- CBOW
- Glove
- FastText
- SkipGram, NGram
- ELMO
- OpenAI GPT
- BERT (Blog)
- Transformers (Paper) (Code) (Blog)
- BERT (Paper)
- Universal Sentence Encoder
- Generative Adversarial Networks (GANs)
- Variational Autoencoders (VAEs)
- Variational Inference (tutorial paper)
- ELBO and Loss Function derivation
- Normalizing Flows
- Triplet Loss
- BLEU Score
- Maxout Networks
- Support Vector Machines
- Maximal-Margin Classifier
- Kernel Trick
- PCA (Explanation)
- PCA using neural network
- Architecture
- Loss Function
- PCA using neural network
- Spatial Transformer Networks
- Gaussian Mixture Models (GMMs)
- Expectation Maximization
- Stanford's CS231n Lecture Notes
- Deep Learning Book (Goodfellow et. al.)
We welcome contributions to add resources such as notes, blogs, or papers for a topic. Feel free to open a pull request for the same!