Search Results for author:
Found 7 papers, 0 papers with code
Half-Space Feature Learning in Neural Networks
Unlike deep linear networks, the DLGN is capable of learning non-linear features (which are then linearly combined), and unlike ReLU networks these features are ultimately simple -- each feature is effectively an indicator function for a region compactly described as an intersection of (number of layers) half-spaces in the input space.
Approximate Linear Programming for Decentralized Policy Iteration in Cooperative Multi-agent Markov Decision Processes
In this work, we consider a cooperative multi-agent Markov decision process (MDP) involving m agents.
Explicitising The Implicit Intrepretability of Deep Neural Networks Via Duality
Using the dual view, in this paper, we rethink the conventional interpretations of DNNs thereby explicitsing the implicit interpretability of DNNs.
Disentangling deep neural networks with rectified linear units using duality
To address `black box'-ness, we propose a novel interpretable counterpart of DNNs with ReLUs namely deep linearly gated networks (DLGN): the pre-activations to the gates are generated by a deep linear network, and the gates are then applied as external masks to learn the weights in a different network.
Neural Path Features and Neural Path Kernel : Understanding the role of gates in deep learning
To this end, we encode the on/off state of the gates of a given input in a novel 'neural path feature' (NPF), and the weights of the DNN are encoded in a novel 'neural path value' (NPV).
Deep Gated Networks: A framework to understand training and generalisation in deep learning
In DGNs, a single neuronal unit has two components namely the pre-activation input (equal to the inner product the weights of the layer and the previous layer outputs), and a gating value which belongs to $[0, 1]$ and the output of the neuronal unit is equal to the multiplication of pre-activation input and the gating value.
Linear Stochastic Approximation: Constant Step-Size and Iterate Averaging
For a given LSA with PR averaging, and data distribution $P$ satisfying the said assumptions, we show that there exists a range of constant step-sizes such that its MSE decays as $O(\frac{1}{t})$.
