Autoencoders (AE) are essential in learning representation of large data (like images) for dimensionality reduction. Images are converted to sparse domain using transforms like Fast Fourier Transform (FFT) or Discrete Cosine Transform (DCT) where information that requires encoding is minimal. By optimally selecting the feature-rich frequencies, we are able to learn the latent vectors more robustly. We successfully show enhanced performance of autoencoders in sparse domain for images.

Global average pooling (GAP) has been used previously to generate class activation maps. The motivation behind AdGAP comes from the fact that the convolutional filters possess position information of the essential features and hence, combination of the feature maps could help us locate the class instances in an image. Our novel architecture generates promising results and unlike previous methods, the architecture is not sensitive to the size of the input image, thus promising wider application.

Recommender systems take inputs from user history, use an internal ranking algorithm to generate results and possibly optimize this ranking based on feedback. However, often the recommender system is unaware of the actual intent of the user and simply provides recommendations dynamically without properly understanding the thought process of the user. An intelligent recommender system is not only useful for the user but also for businesses which want to learn the tendencies of their users. Finding out tendencies or intents of a user is a difficult problem to solve. Keeping this in mind, we sought out to create an intelligent system which will keep track of the user's activity on a web-application as well as determine the intent of the user in each session. We devised a way to encode the user's activity through the sessions. Then, we have represented the information seen by the user in a high dimensional format which is reduced to lower dimensions using tensor factorization techniques. The aspect of intent awareness (or scoring) is dealt with at this stage. Finally, combining the user activity data with the contextual information gives the recommendation score. The final recommendations are then ranked using filtering and collaborative recommendation techniques to show the top-k recommendations to the user. A provision for feedback is also envisioned in the current system which informs the model to update the various weights in the recommender system. Our overall model aims to combine both frequency-based and context-based recommendation systems and quantify the intent of a user to provide better recommendations. We ran experiments on real-world timestamped user activity data, in the setting of recommending reports to the users of a business analytics tool and the results are better than the baselines. We also tuned certain aspects of our model to arrive at optimized results.

Power grids are one of the most important components of infrastructure in today's world. Every nation is dependent on the security and stability of its own power grid to provide electricity to the households and industries. A malfunction of even a small part of a power grid can cause loss of productivity, revenue and in some cases even life. Thus, it is imperative to design a system which can detect the health of the power grid and take protective measures accordingly even before a serious anomaly takes place. To achieve this objective, we have set out to create an artificially intelligent system which can analyze the grid information at any given time and determine the health of the grid through the usage of sophisticated formal models and novel machine learning techniques like recurrent neural networks. Our system simulates grid conditions including stimuli like faults, generator output fluctuations, load fluctuations using Siemens PSS/E software and this data is trained using various classifiers like SVM, LSTM and subsequently tested. The results are excellent with our methods giving very high accuracy for the data. This model can easily be scaled to handle larger and more complex grid architectures.

Non-availability of reliable and sustainable electric power is a major problem in the developing world. Renewable energy sources like solar are not very lucrative in the current stage due to various uncertainties like weather, storage, land use among others. There also exists various other issues like mis-commitment of power, absence of intelligent fault analysis, congestion, etc. In this paper, we propose a novel deep learning-based system for predicting faults and selecting power generators optimally so as to reduce costs and ensure higher reliability in solar power systems. The results are highly encouraging and they suggest that the approaches proposed in this paper have the potential to be applied successfully in the developing world.

Handwriting is a skill learned by humans from a very early age. The ability to develop one’s own unique handwriting as well as mimic another person’s handwriting is a task learned by the brain with practice. This paper deals with this very problem where an intelligent system tries to learn the handwriting of an entity using Generative Adversarial Networks (GANs). We propose a modified architecture of DCGAN (Radford, Metz, and Chintala 2015) to achieve this. We also discuss about applying reinforcement learning techniques to achieve faster learning. Our algorithm hopes to give new insights in this area and its uses include identification of forged documents, signature verification, computer generated art, digitization of documents among others. Our early implementation of the algorithm illustrates a good performance with MNIST datasets.