Competencies: AI & ML > Deep Learning

Neural Network Fundamentals

Neurons, layers, activation functions, forward/backward propagation, architecture design.

Critical

ML Engineer, Research Scientist

PyTorch

Tensors, autograd, nn.Module, DataLoader, training loops, GPU acceleration, TorchScript.

Critical

ML Engineer, Research Scientist

TensorFlow/Keras

tf.keras API, custom layers, tf.data, SavedModel, TensorBoard, TPU training.

High

ML Engineer, Data Scientist

Convolutional Neural Networks

Convolution, pooling, receptive field, CNN architectures (ResNet, VGG, EfficientNet).

Critical

ML Engineer, CV Engineer

Recurrent Neural Networks

RNN, LSTM, GRU, sequence modeling, vanishing gradients, bidirectional RNNs.

High

ML Engineer, NLP Engineer

Transformers

Attention mechanism, self-attention, positional encoding, encoder-decoder architecture.

Critical

ML Engineer, Research Scientist

Transfer Learning

Pretrained models, fine-tuning, feature extraction, domain adaptation.

Critical

ML Engineer, Data Scientist

Hyperparameter Tuning

Learning rate, batch size, architecture search, Optuna, Ray Tune, wandb sweeps.

High

ML Engineer, Data Scientist

Training at Scale

Distributed training, data parallelism, model parallelism, mixed precision, gradient accumulation.

High

ML Engineer, MLOps Engineer

Model Debugging

Loss curves, gradient analysis, activation visualization, overfitting diagnosis.

High

ML Engineer, Data Scientist

No personal status recorded

 — 

 — 

 — 

 —