Introduction to Deep Learning · HIT

Final   35% of the grade with a short oral defense · proposal around week 8 · due week 13

Final project examples

The final project takes a task end to end with any architecture family from the course. Work solo or in a pair: frame the task, build a suitable network, train and tune it, diagnose failures, and report results. The examples below span vision, sequences, and representation learning; or propose a variant instead.

Deliverables.

📋Ten examples

01Transfer-learning regimes

Data: A small image dataset.

Idea: When does transfer learning help?

Methods: Compare from-scratch, frozen-features, and fine-tuning a pretrained backbone under a fixed budget.

Evaluation: Accuracy versus training cost across regimes; characterize when transfer wins.

Stretch goal: Vary the target dataset size and find the crossover point.

02Sentiment classification with LSTM/GRU

Data: A small text sentiment set (for example an IMDB or SST subset).

Idea: Sequence classification.

Methods: An embedding layer with an LSTM or GRU.

Evaluation: Accuracy and F1; compare LSTM versus GRU and long versus short inputs.

Stretch goal: Add pretrained word embeddings.

03Character-level language model

Data: A plain-text corpus (for example a public-domain book).

Idea: Generate text with a recurrent net.

Methods: A character-level RNN or LSTM.

Evaluation: Held-out perplexity plus qualitative samples; study the sampling temperature.

Stretch goal: Compare an RNN with an LSTM at matched size.

04Image denoising autoencoder

Data: MNIST or FashionMNIST with added noise.

Idea: Denoise images and inspect the latent space.

Methods: A convolutional autoencoder.

Evaluation: Reconstruction error and latent-space structure (clusters, interpolation).

Stretch goal: Use reconstruction error for anomaly detection.

05Contrastive representation learning

Data: CIFAR-10 (labels withheld for pretraining).

Idea: Learn features without labels.

Methods: A SimCLR-style setup: augmentations, a contrastive loss, and a linear probe.

Evaluation: Linear-probe accuracy versus a supervised baseline at low label counts.

Stretch goal: Compare two augmentation policies and their effect on the representation.

06CNN + RNN encoder-decoder

Data: A small image-to-sequence toy dataset.

Idea: Combine vision and sequence models.

Methods: A CNN encoder feeding an RNN decoder.

Evaluation: A task-appropriate metric; ablate the encoder.

Stretch goal: Add an attention-free pooling variant and compare.

07Time-series forecasting

Data: A public time series (for example energy or weather).

Idea: Forecast future values.

Methods: An RNN or LSTM against a naive or linear baseline.

Evaluation: MAE and RMSE; study how error grows with the forecast horizon.

Stretch goal: Add exogenous features and measure the gain.

08Audio classification via spectrograms

Data: A small audio set (for example an ESC-50 or UrbanSound subset).

Idea: Treat spectrograms as images.

Methods: A CNN, optionally a pretrained image backbone.

Evaluation: Classification accuracy; try time and frequency augmentation.

Stretch goal: Compare raw-waveform input against the spectrogram.

09An empirical optimization study

Data: A task of the student's choice.

Idea: A careful, controlled empirical study.

Methods: A fixed architecture with a rigorous protocol over optimizers and regularizers.

Evaluation: Curves with multiple seeds and visible variance, leading to clear conclusions.

Stretch goal: Add confidence intervals via bootstrapping.

10An end-to-end applied problem

Data: A Kaggle-style image or tabular problem.

Idea: Solve a real problem end to end.

Methods: An appropriate neural architecture with a sound train/validation/test protocol.

Evaluation: A leaderboard-style metric reported honestly on a held-out split.

Stretch goal: Compare against a strong non-neural baseline.

Mid-term mini-project examples Syllabus Course home