Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1]
Toward a neuro-inspired creative decoder
Authors: Payel Das, Brian Quanz, Pin-Yu Chen, Jae-wook Ahn, Dhruv Shah
IJCAI 2020 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our experiments on different image datasets (MNIST, FMNIST, MNIST+FMNIST, Wiki Art and Celeb A) reveal that atypical co-activation of highly activated and weakly activated neurons in a deep decoder promotes generation of novel and meaningful artifacts. |
| Researcher Affiliation | Industry | Payel Das , Brian Quanz , Pin-Yu Chen , Jae-wook Ahn and Dhruv Shah IBM Research, Yorktown Heights, NY, USA EMAIL, EMAIL, EMAIL, EMAIL |
| Pseudocode | Yes | Algorithm 1 Low-active method |
| Open Source Code | No | The paper does not provide an explicit statement or link indicating that the source code for the described methodology is publicly available. |
| Open Datasets | Yes | We show the performance of the proposed method against MNIST digits , FMINST fashion objects , and on a combined MNIST plus FMINST dataset. We also present results on the Wiki Art art images and Celeb A faces. |
| Dataset Splits | No | The paper uses standard datasets like MNIST and FMNIST and mentions training and testing but does not explicitly state the specific dataset splits (e.g., percentages or counts for train/validation/test sets) used for reproducibility. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used to run the experiments, such as GPU/CPU models or memory specifications. |
| Software Dependencies | No | The paper mentions deep learning frameworks like VAE and GAN but does not specify software dependencies with version numbers (e.g., Python, PyTorch, or TensorFlow versions). |
| Experiment Setup | Yes | For F/MNIST the encoder network consisted of 3 fully-connected layers (1000, 500, 250) before the z output (50 for F/MNIST and 100 for the combination), with the decoder architecture the reverse of the encoder. RELU activations were used; dropout equal to 0.10 for fully-connected layers was used during training only. ... Unless otherwise stated, results in the main paper were obtained by perturbing five neurons during decoding. For the low-active method, we used neurons whose activations (see Method Section) were within the 1st and 15th percentiles of the neuron percent activations (ak j ) for the layer. |