[ ] Abstract (0.4 pages) and Introduction (0.6 page). Why is that important, read a recent papers, cite them. Focus: N-top moviesMohan
[x] Data analysis: (1 page) Tanya
[ ] Models (theory, related work). Make them use the SAME input/features.
YOUTUBE NET (0.5 pages) Dawn Add User Id and Movie title
EUM-CT NET (0.5 pages) Abby,
BASELINES (Random and KNN with Cosine Similarity) (0.5 page) Mohan
[ ] Experiments
Models with configuration, hyper-parameters, learning rate, graph loss vs something etc.
YOUTUBE NET (0.5 pages) Dawn (Mention that you implemented it from scratch)
EUM-CT NET (0.5 pages) Abby
[ ] Evaluation (1 page). Combine all result together (Precision, recall, graph) for
YOUTUBE NET, EUM-CT NET, BASELINES (Random and KNN with Cosine Similarity). Together discussion.Echo is responsible for research what we need to reflect in that section and write it down
[ ] TRIAL section. Briefly describe what we tried (Auto Encoder, Collaborative Filtering, BiRNN) (0.3 pages per each, 1 pages in total) Tanya, Echo, Mohan.
[ ] Conclusion future work (0.5 page) Echo
[ ] Contribution, a few sentences about what each person has personally done All
We are going to write the report, similar for this, please everyone READ it completely and pay attention on MAIN details: https://github.com/tmozgach/movie_rec_sys/issues/7
Select one topic and write your name near that:
[ ] Abstract (0.4 pages) and Introduction (0.6 page). Why is that important, read a recent papers, cite them. Focus: N-top movies Mohan
[x] Data analysis: (1 page) Tanya
[ ] Models (theory, related work). Make them use the SAME input/features. YOUTUBE NET (0.5 pages) Dawn Add User Id and Movie title EUM-CT NET (0.5 pages) Abby, BASELINES (Random and KNN with Cosine Similarity) (0.5 page) Mohan
[ ] Experiments Models with configuration, hyper-parameters, learning rate, graph loss vs something etc. YOUTUBE NET (0.5 pages) Dawn (Mention that you implemented it from scratch) EUM-CT NET (0.5 pages) Abby
[ ] Evaluation (1 page). Combine all result together (Precision, recall, graph) for YOUTUBE NET, EUM-CT NET, BASELINES (Random and KNN with Cosine Similarity). Together discussion. Echo is responsible for research what we need to reflect in that section and write it down
[ ] TRIAL section. Briefly describe what we tried (Auto Encoder, Collaborative Filtering, BiRNN) (0.3 pages per each, 1 pages in total) Tanya, Echo, Mohan.
[ ] Conclusion future work (0.5 page) Echo
[ ] Contribution, a few sentences about what each person has personally done All